Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4845 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0200. Min Range: -7.0200
Max Act: 7.0200. Min Act: -0.1700
Data Index: 1060219 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.7075. Min Act: -0.1700
Data Index: 6313030 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.5825. Min Act: -0.1700
Data Index: 5073448 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.4263. Min Act: -0.1700
Data Index: 8152508 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.3950. Min Act: -0.1700
Data Index: 5606735 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.3013. Min Act: -0.1700
Data Index: 8682479 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.3325. Min Act: -0.1700
Data Index: 552715 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.3013. Min Act: -0.1700
Data Index: 7897397 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.2700. Min Act: -0.1700
Data Index: 2282768 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.2388. Min Act: -0.1700
Data Index: 4410910 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.2075. Min Act: -0.1700
Data Index: 7231256 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.2075. Min Act: -0.1700
Data Index: 5104141 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1763. Min Act: -0.1700
Data Index: 8682483 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1763. Min Act: -0.1700
Data Index: 2729293 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1763. Min Act: -0.1700
Data Index: 2985373 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1450. Min Act: -0.1700
Data Index: 928306 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1450. Min Act: -0.1700
Data Index: 7216517 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1450. Min Act: -0.1700
Data Index: 7678616 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.1138. Min Act: -0.1700
Data Index: 3773122 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0200. Min Range: -7.0200
Max Act: 6.0825. Min Act: -0.1700
Data Index: 393025 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19