Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1195 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2593. Min Act: -0.1700
Data Index: 790393 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2121. Min Act: -0.1700
Data Index: 3972795 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.2279. Min Act: -0.1700
Data Index: 5191943 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 2171180 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1335. Min Act: -0.1700
Data Index: 2244633 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1335. Min Act: -0.1700
Data Index: 5103967 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1335. Min Act: -0.1700
Data Index: 5020897 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 1097894 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1177. Min Act: -0.1700
Data Index: 8687556 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1020. Min Act: -0.1700
Data Index: 3324519 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1020. Min Act: -0.1700
Data Index: 7973097 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.1020. Min Act: -0.1700
Data Index: 3083098 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0862. Min Act: -0.1700
Data Index: 4073917 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 4598649 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 6564835 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 2384278 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 6358495 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 6057544 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0704. Min Act: -0.1700
Data Index: 4373744 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2593. Min Range: -3.2593
Max Act: 3.0547. Min Act: -0.1700
Data Index: 2595166 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #19