Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3955 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5544. Min Range: -10.5544
Max Act: 10.5544. Min Act: -0.1700
Data Index: 8555018 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5544. Min Range: -10.5544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 585905 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5544. Min Range: -10.5544
Max Act: 10.0544. Min Act: -0.1700
Data Index: 3808525 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.9919. Min Act: -0.1700
Data Index: 7262427 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.9919. Min Act: -0.1700
Data Index: 7255200 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.9294. Min Act: -0.1700
Data Index: 5345766 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.8669. Min Act: -0.1700
Data Index: 3896215 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.8669. Min Act: -0.1700
Data Index: 8399905 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.7419. Min Act: -0.1700
Data Index: 8577662 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.7419. Min Act: -0.1700
Data Index: 2024172 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6794. Min Act: -0.1700
Data Index: 4024561 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6794. Min Act: -0.1699
Data Index: 161986 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6169. Min Act: -0.1700
Data Index: 6065893 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6794. Min Act: -0.1700
Data Index: 4628364 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6794. Min Act: -0.1700
Data Index: 5521744 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6169. Min Act: -0.1700
Data Index: 2638354 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6169. Min Act: -0.1700
Data Index: 8209605 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6169. Min Act: -0.1700
Data Index: 613024 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6794. Min Act: -0.1700
Data Index: 7599949 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5544. Min Range: -10.5544
Max Act: 9.6169. Min Act: -0.1700
Data Index: 2924767 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19