Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3308 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.1911. Min Act: -0.1700
Data Index: 2606667 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.1286. Min Act: -0.1700
Data Index: 3377833 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0974. Min Act: -0.1700
Data Index: 1607185 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0661. Min Act: -0.1700
Data Index: 805872 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0661. Min Act: -0.1700
Data Index: 7183662 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0661. Min Act: -0.1700
Data Index: 870490 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0661. Min Act: -0.1700
Data Index: 6742410 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 1642503 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 7020880 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 3462630 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 8266993 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 6594228 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 4792438 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0349. Min Act: -0.1700
Data Index: 6655949 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0036. Min Act: -0.1700
Data Index: 4033610 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5061318 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0036. Min Act: -0.1700
Data Index: 5886303 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1911. Min Range: -7.1911
Max Act: 7.0036. Min Act: -0.1700
Data Index: 2518073 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1911. Min Range: -7.1911
Max Act: 6.9724. Min Act: -0.1700
Data Index: 1559621 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1911. Min Range: -7.1911
Max Act: 6.9724. Min Act: -0.1700
Data Index: 1619737 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #19