Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5904 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3531. Min Range: -6.3531
Max Act: 6.3531. Min Act: -0.1700
Data Index: 8081086 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3531. Min Range: -6.3531
Max Act: 6.2594. Min Act: -0.1700
Data Index: 6349425 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3531. Min Range: -6.3531
Max Act: 6.1656. Min Act: -0.1700
Data Index: 6292368 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.8531. Min Act: -0.1700
Data Index: 4777303 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.8219. Min Act: -0.1700
Data Index: 310324 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.7594. Min Act: -0.1700
Data Index: 7539309 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6969. Min Act: -0.1700
Data Index: 6150053 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6656. Min Act: -0.1700
Data Index: 3892334 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6344. Min Act: -0.1700
Data Index: 7717539 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6344. Min Act: -0.1700
Data Index: 2074599 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6344. Min Act: -0.1700
Data Index: 7821395 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6344. Min Act: -0.1700
Data Index: 1400225 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6344. Min Act: -0.1700
Data Index: 349919 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6031. Min Act: -0.1700
Data Index: 4759632 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6031. Min Act: -0.1700
Data Index: 4969476 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6031. Min Act: -0.1700
Data Index: 1700816 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.5719. Min Act: -0.1700
Data Index: 2461467 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6031. Min Act: -0.1700
Data Index: 2887740 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.6031. Min Act: -0.1700
Data Index: 8026912 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3531. Min Range: -6.3531
Max Act: 5.5719. Min Act: -0.1700
Data Index: 8656126 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #19