Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4517 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.6273. Min Act: -0.1700
Data Index: 919733 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.5648. Min Act: -0.1700
Data Index: 1600079 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.5023. Min Act: -0.1700
Data Index: 79121 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4711. Min Act: -0.1700
Data Index: 5128616 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4398. Min Act: -0.1700
Data Index: 4519011 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4398. Min Act: -0.1700
Data Index: 5172132 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 1663370 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 6252279 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 6344745 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3773. Min Act: -0.1700
Data Index: 7896592 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 630588 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3773. Min Act: -0.1700
Data Index: 1917972 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3773. Min Act: -0.1700
Data Index: 1853055 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.4086. Min Act: -0.1700
Data Index: 4707130 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 3657017 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 33315 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 2905503 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 925518 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 357171 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6273. Min Range: -5.6273
Max Act: 5.3461. Min Act: -0.1700
Data Index: 1339144 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19