Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2494 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.9577. Min Act: -0.1700
Data Index: 2842455 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.8952. Min Act: -0.1700
Data Index: 7881222 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7077. Min Act: -0.1700
Data Index: 4805722 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7702. Min Act: -0.1700
Data Index: 2877651 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7702. Min Act: -0.1700
Data Index: 1470619 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7077. Min Act: -0.1700
Data Index: 8542724 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7077. Min Act: -0.1700
Data Index: 4546311 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7077. Min Act: -0.1700
Data Index: 6336840 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.7077. Min Act: -0.1700
Data Index: 3433547 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 5196392 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 7559928 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 4291339 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 8374315 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 468285 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 4426736 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 4972243 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 6358255 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.6452. Min Act: -0.1700
Data Index: 7237779 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.5827. Min Act: -0.1700
Data Index: 5728454 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9577. Min Range: -9.9577
Max Act: 9.5827. Min Act: -0.1700
Data Index: 6881154 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #19