Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4353 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2843. Min Range: -9.2843
Max Act: 9.2843. Min Act: -0.1700
Data Index: 3010624 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2843. Min Range: -9.2843
Max Act: 9.2843. Min Act: -0.1700
Data Index: 6419551 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2843. Min Range: -9.2843
Max Act: 9.1593. Min Act: -0.1700
Data Index: 3111127 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2843. Min Range: -9.2843
Max Act: 9.0968. Min Act: -0.1700
Data Index: 2287740 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.9718. Min Act: -0.1700
Data Index: 5214978 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2843. Min Range: -9.2843
Max Act: 9.0343. Min Act: -0.1700
Data Index: 8248841 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.9093. Min Act: -0.1700
Data Index: 8746582 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.9093. Min Act: -0.1700
Data Index: 8320695 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.9093. Min Act: -0.1700
Data Index: 4924365 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.8468. Min Act: -0.1700
Data Index: 3690959 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.8468. Min Act: -0.1700
Data Index: 1396491 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.8468. Min Act: -0.1700
Data Index: 7215279 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 5060182 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 7085774 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 2975312 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 737415 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 4043567 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7843. Min Act: -0.1700
Data Index: 6631208 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7218. Min Act: -0.1700
Data Index: 1811821 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2843. Min Range: -9.2843
Max Act: 8.7218. Min Act: -0.1700
Data Index: 6067637 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19