Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3057 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.2382. Min Act: -0.1700
Data Index: 3408938 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.1757. Min Act: -0.1700
Data Index: 4001186 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.1132. Min Act: -0.1700
Data Index: 4223279 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.1132. Min Act: -0.1700
Data Index: 4194976 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.1132. Min Act: -0.1700
Data Index: 243581 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.0506. Min Act: -0.1700
Data Index: 3401283 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.0194. Min Act: -0.1700
Data Index: 3899518 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2382. Min Range: -4.2382
Max Act: 4.0194. Min Act: -0.1700
Data Index: 4842078 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.9569. Min Act: -0.1700
Data Index: 7120453 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.9881. Min Act: -0.1700
Data Index: 1654994 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.9569. Min Act: -0.1700
Data Index: 303174 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8943. Min Act: -0.1700
Data Index: 1129028 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.9256. Min Act: -0.1700
Data Index: 2069212 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.9256. Min Act: -0.1700
Data Index: 4901935 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8943. Min Act: -0.1700
Data Index: 3245235 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8943. Min Act: -0.1700
Data Index: 5256346 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8787. Min Act: -0.1700
Data Index: 137010 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8943. Min Act: -0.1700
Data Index: 3416214 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8787. Min Act: -0.1700
Data Index: 5256343 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2382. Min Range: -4.2382
Max Act: 3.8631. Min Act: -0.1700
Data Index: 1955218 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #19