Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2001 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.6224. Min Act: -0.1700
Data Index: 745694 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.6224. Min Act: -0.1700
Data Index: 8096692 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.5911. Min Act: -0.1700
Data Index: 8486514 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.5754. Min Act: -0.1700
Data Index: 58359 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4971. Min Act: -0.1700
Data Index: 8252156 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4815. Min Act: -0.1700
Data Index: 5140713 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4501. Min Act: -0.1700
Data Index: 4056117 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4501. Min Act: -0.1700
Data Index: 6782486 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4345. Min Act: -0.1700
Data Index: 7079740 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4501. Min Act: -0.1700
Data Index: 8820189 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4345. Min Act: -0.1700
Data Index: 2049296 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4501. Min Act: -0.1700
Data Index: 5192758 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4345. Min Act: -0.1700
Data Index: 8358141 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4188. Min Act: -0.1700
Data Index: 5962209 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4188. Min Act: -0.1700
Data Index: 7483455 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4501. Min Act: -0.1700
Data Index: 6147053 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4031. Min Act: -0.1700
Data Index: 2324398 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4188. Min Act: -0.1700
Data Index: 2805762 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.4031. Min Act: -0.1700
Data Index: 6576778 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6224. Min Range: -3.6224
Max Act: 3.3404. Min Act: -0.1700
Data Index: 7501800 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #19