Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3318 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3531. Min Range: -7.3531
Max Act: 7.3531. Min Act: -0.1700
Data Index: 5393257 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3531. Min Range: -7.3531
Max Act: 7.1031. Min Act: -0.1700
Data Index: 5023446 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.9156. Min Act: -0.1700
Data Index: 2466859 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.8531. Min Act: -0.1700
Data Index: 246667 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.8843. Min Act: -0.1700
Data Index: 3677418 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.8218. Min Act: -0.1700
Data Index: 6524896 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7906. Min Act: -0.1700
Data Index: 748298 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7906. Min Act: -0.1700
Data Index: 5778941 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7593. Min Act: -0.1700
Data Index: 8253319 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7593. Min Act: -0.1700
Data Index: 5667529 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7593. Min Act: -0.1700
Data Index: 5339416 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7281. Min Act: -0.1700
Data Index: 8801782 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.7281. Min Act: -0.1700
Data Index: 4710385 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6968. Min Act: -0.1700
Data Index: 2268874 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6968. Min Act: -0.1700
Data Index: 3807797 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6968. Min Act: -0.1700
Data Index: 4814736 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6343. Min Act: -0.1700
Data Index: 5711582 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6656. Min Act: -0.1700
Data Index: 6949599 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6343. Min Act: -0.1700
Data Index: 1480239 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3531. Min Range: -7.3531
Max Act: 6.6343. Min Act: -0.1700
Data Index: 1728773 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #19