Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 136 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.5806. Min Act: -0.1700
Data Index: 1414268 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.5493. Min Act: -0.1700
Data Index: 623904 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.4556. Min Act: -0.1700
Data Index: 3998407 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.4243. Min Act: -0.1700
Data Index: 1859857 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.4556. Min Act: -0.1700
Data Index: 6999110 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.4556. Min Act: -0.1700
Data Index: 3239990 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.4243. Min Act: -0.1700
Data Index: 8176594 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3618. Min Act: -0.1700
Data Index: 5455283 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3618. Min Act: -0.1700
Data Index: 3068799 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3618. Min Act: -0.1700
Data Index: 770906 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3618. Min Act: -0.1700
Data Index: 6829308 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3306. Min Act: -0.1700
Data Index: 8362443 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2993. Min Act: -0.1700
Data Index: 2085693 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3306. Min Act: -0.1700
Data Index: 5733359 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.3306. Min Act: -0.1700
Data Index: 7638092 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2681. Min Act: -0.1700
Data Index: 939793 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2681. Min Act: -0.1700
Data Index: 6309375 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2681. Min Act: -0.1700
Data Index: 4457636 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2681. Min Act: -0.1700
Data Index: 297681 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5806. Min Range: -6.5806
Max Act: 6.2681. Min Act: -0.1700
Data Index: 4051355 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #19