Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3526 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.6814. Min Act: -0.1700
Data Index: 3977783 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.6501. Min Act: -0.1700
Data Index: 8634291 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.4626. Min Act: -0.1700
Data Index: 1706547 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.4001. Min Act: -0.1700
Data Index: 1197183 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.4314. Min Act: -0.1700
Data Index: 1933517 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.4001. Min Act: -0.1700
Data Index: 8188086 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3689. Min Act: -0.1700
Data Index: 2316378 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3689. Min Act: -0.1698
Data Index: 6351515 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3376. Min Act: -0.1700
Data Index: 5048233 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3064. Min Act: -0.1700
Data Index: 2793167 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3064. Min Act: -0.1700
Data Index: 5792536 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3064. Min Act: -0.1700
Data Index: 7549776 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3064. Min Act: -0.1700
Data Index: 1034211 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.2751. Min Act: -0.1699
Data Index: 4393422 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.3064. Min Act: -0.1700
Data Index: 4234923 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.2439. Min Act: -0.1700
Data Index: 8390996 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.2751. Min Act: -0.1700
Data Index: 8335494 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.2751. Min Act: -0.1700
Data Index: 5108876 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.2126. Min Act: -0.1700
Data Index: 614530 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6814. Min Range: -6.6814
Max Act: 6.1814. Min Act: -0.1700
Data Index: 3545319 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19