Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3462 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4152. Min Range: -8.4152
Max Act: 8.4152. Min Act: -0.1700
Data Index: 1570038 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4152. Min Range: -8.4152
Max Act: 8.0402. Min Act: -0.1700
Data Index: 4741861 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4152. Min Range: -8.4152
Max Act: 8.0402. Min Act: -0.1700
Data Index: 168308 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.7277. Min Act: -0.1700
Data Index: 1540394 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.6965. Min Act: -0.1700
Data Index: 5676868 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.6652. Min Act: -0.1700
Data Index: 1318259 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.6340. Min Act: -0.1700
Data Index: 7112647 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.6652. Min Act: -0.1700
Data Index: 47684 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.5715. Min Act: -0.1700
Data Index: 7240639 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.5715. Min Act: -0.1700
Data Index: 790420 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.5715. Min Act: -0.1700
Data Index: 4381693 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.5715. Min Act: -0.1700
Data Index: 173007 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.5715. Min Act: -0.1700
Data Index: 5206063 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4777. Min Act: -0.1700
Data Index: 1540983 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4777. Min Act: -0.1700
Data Index: 2367316 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4777. Min Act: -0.1700
Data Index: 7396806 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4465. Min Act: -0.1700
Data Index: 109912 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4152. Min Act: -0.1700
Data Index: 2142535 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4152. Min Act: -0.1700
Data Index: 4116359 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4152. Min Range: -8.4152
Max Act: 7.4465. Min Act: -0.1700
Data Index: 1665192 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #19