Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2098 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.5360. Min Act: -0.1700
Data Index: 1632072 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.4110. Min Act: -0.1700
Data Index: 3786016 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.2860. Min Act: -0.1700
Data Index: 3373747 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.0985. Min Act: -0.1700
Data Index: 8359530 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.0985. Min Act: -0.1700
Data Index: 7800655 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.0360. Min Act: -0.1700
Data Index: 3418266 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5360. Min Range: -8.5360
Max Act: 8.0360. Min Act: -0.1700
Data Index: 6207947 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 6209055 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 8439849 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 4970919 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 6207937 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 7715742 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9735. Min Act: -0.1700
Data Index: 2264935 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 44374 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 830070 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 4112003 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 485417 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 6360737 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.9110. Min Act: -0.1700
Data Index: 3418265 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5360. Min Range: -8.5360
Max Act: 7.8485. Min Act: -0.1700
Data Index: 28529 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19