Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 35 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0839. Min Range: -5.0839
Max Act: 5.0527. Min Act: -0.1700
Data Index: 1277861 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0839. Min Range: -5.0839
Max Act: 5.0839. Min Act: -0.1700
Data Index: 3265371 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.9277. Min Act: -0.1700
Data Index: 8168418 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8339. Min Act: -0.1700
Data Index: 8304520 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8652. Min Act: -0.1700
Data Index: 249930 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8652. Min Act: -0.1700
Data Index: 866145 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5784904 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8339. Min Act: -0.1700
Data Index: 5845733 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8339. Min Act: -0.1700
Data Index: 6199110 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8652. Min Act: -0.1700
Data Index: 5252232 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7402. Min Act: -0.1700
Data Index: 3031308 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8027. Min Act: -0.1700
Data Index: 7893109 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8027. Min Act: -0.1700
Data Index: 5041384 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7402. Min Act: -0.1700
Data Index: 6531307 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7402. Min Act: -0.1700
Data Index: 764886 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7402. Min Act: -0.1700
Data Index: 8215990 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7714. Min Act: -0.1700
Data Index: 7567453 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.8027. Min Act: -0.1700
Data Index: 638754 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7402. Min Act: -0.1700
Data Index: 5890524 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0839. Min Range: -5.0839
Max Act: 4.7089. Min Act: -0.1700
Data Index: 6381423 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19