Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2985 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.6198. Min Act: -0.1700
Data Index: 7293122 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.6198. Min Act: -0.1698
Data Index: 7391422 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.5554. Min Act: -0.1700
Data Index: 4774455 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.5069. Min Act: -0.1700
Data Index: 4965965 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.5231. Min Act: -0.1699
Data Index: 2468266 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.5069. Min Act: -0.1700
Data Index: 8250439 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.5069. Min Act: -0.1700
Data Index: 6799992 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4745. Min Act: -0.1700
Data Index: 5109131 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4745. Min Act: -0.1700
Data Index: 4709249 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4907. Min Act: -0.1700
Data Index: 5102445 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4420. Min Act: -0.1697
Data Index: 7391421 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4582. Min Act: -0.1700
Data Index: 38612 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4582. Min Act: -0.1700
Data Index: 7773427 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4582. Min Act: -0.1700
Data Index: 2607181 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4582. Min Act: -0.1700
Data Index: 487002 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4420. Min Act: -0.1700
Data Index: 7232958 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4420. Min Act: -0.1700
Data Index: 2744451 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4257. Min Act: -0.1700
Data Index: 2856629 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4257. Min Act: -0.1700
Data Index: 2533320 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6198. Min Range: -2.6198
Max Act: 2.4257. Min Act: -0.1700
Data Index: 3799939 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19