Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1940 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.3770. Min Act: -0.1700
Data Index: 8716496 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.3145. Min Act: -0.1700
Data Index: 2756778 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.3145. Min Act: -0.1700
Data Index: 4338585 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.1895. Min Act: -0.1700
Data Index: 8112986 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.1270. Min Act: -0.1700
Data Index: 5142798 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.1895. Min Act: -0.1700
Data Index: 4639225 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0645. Min Act: -0.1700
Data Index: 1534524 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0645. Min Act: -0.1700
Data Index: 3958438 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0645. Min Act: -0.1700
Data Index: 4116072 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0645. Min Act: -0.1700
Data Index: 6614146 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0020. Min Act: -0.1700
Data Index: 2541162 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3770. Min Range: -9.3770
Max Act: 9.0020. Min Act: -0.1700
Data Index: 865282 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.9395. Min Act: -0.1700
Data Index: 505573 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.9395. Min Act: -0.1700
Data Index: 4417337 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8770. Min Act: -0.1700
Data Index: 7319204 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8770. Min Act: -0.1700
Data Index: 7526682 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8770. Min Act: -0.1700
Data Index: 1724272 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8770. Min Act: -0.1700
Data Index: 2515426 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8145. Min Act: -0.1700
Data Index: 455037 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3770. Min Range: -9.3770
Max Act: 8.8145. Min Act: -0.1700
Data Index: 793148 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #19