Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 37 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.8748. Min Range: -11.8748
Max Act: 11.8748. Min Act: -0.1700
Data Index: 8466911 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.8748. Min Range: -11.8748
Max Act: 11.1248. Min Act: -0.1700
Data Index: 6867413 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.8748. Min Range: -11.8748
Max Act: 11.0623. Min Act: -0.1700
Data Index: 3557708 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.8748. Min Range: -11.8748
Max Act: 11.0623. Min Act: -0.1700
Data Index: 8613054 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.9998. Min Act: -0.1700
Data Index: 1320890 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.8123. Min Act: -0.1700
Data Index: 2437223 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.8748. Min Act: -0.1700
Data Index: 6594062 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.8748. Min Act: -0.1700
Data Index: 8155255 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.8123. Min Act: -0.1700
Data Index: 820458 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.8123. Min Act: -0.1700
Data Index: 4333170 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.7498. Min Act: -0.1700
Data Index: 3002397 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.7498. Min Act: -0.1700
Data Index: 7306668 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.6873. Min Act: -0.1700
Data Index: 2245451 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.7498. Min Act: -0.1700
Data Index: 7711766 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.6873. Min Act: -0.1700
Data Index: 2618103 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.6873. Min Act: -0.1700
Data Index: 3002398 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.6248. Min Act: -0.1700
Data Index: 1313495 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.6248. Min Act: -0.1700
Data Index: 1512732 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.5623. Min Act: -0.1700
Data Index: 2995640 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.8748. Min Range: -11.8748
Max Act: 10.4998. Min Act: -0.1700
Data Index: 537779 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19