Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2908 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.2698. Min Act: -0.1700
Data Index: 3433022 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.2385. Min Act: -0.1700
Data Index: 845620 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.2385. Min Act: -0.1700
Data Index: 8377022 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0510. Min Act: -0.1700
Data Index: 8591075 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0510. Min Act: -0.1700
Data Index: 3122927 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 5624034 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0510. Min Act: -0.1700
Data Index: 5894111 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 3843518 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 3648710 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 4982172 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 6467093 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2698. Min Range: -4.2698
Max Act: 4.0197. Min Act: -0.1700
Data Index: 4667265 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6467092 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6304659 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 6942381 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 3715014 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 758183 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 3122928 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 2936845 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2698. Min Range: -4.2698
Max Act: 3.9885. Min Act: -0.1700
Data Index: 5612271 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #19