Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 904 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9289. Min Act: -0.1700
Data Index: 268462 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9289. Min Act: -0.1700
Data Index: 291055 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9289. Min Act: -0.1700
Data Index: 796783 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 1610529 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.8972. Min Act: -0.1700
Data Index: 1922051 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 2982391 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 5888504 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 974983 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 83369 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 2458717 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 1674207 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 2056808 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 188233 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 1610532 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 1132772 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 5780450 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 5521579 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 344095 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 5462735 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9289. Min Range: -2.9289
Max Act: 2.9130. Min Act: -0.1700
Data Index: 141752 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19