Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0183. Min Range: -3.0183
Max Act: 3.0183. Min Act: -0.1700
Data Index: 4993227 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.9708. Min Act: -0.1700
Data Index: 4225079 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.9075. Min Act: -0.1700
Data Index: 487586 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.8281. Min Act: -0.1700
Data Index: 8087255 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.8281. Min Act: -0.1700
Data Index: 4993231 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7803. Min Act: -0.1700
Data Index: 8752176 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7803. Min Act: -0.1700
Data Index: 8752172 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7644. Min Act: -0.1700
Data Index: 250983 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7484. Min Act: -0.1700
Data Index: 4670012 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7325. Min Act: -0.1700
Data Index: 1610850 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.7005. Min Act: -0.1700
Data Index: 5768103 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6685. Min Act: -0.1700
Data Index: 5420671 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6364. Min Act: -0.1700
Data Index: 5951708 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6364. Min Act: -0.1700
Data Index: 4052937 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6364. Min Act: -0.1700
Data Index: 4993229 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6524. Min Act: -0.1700
Data Index: 3352942 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6203. Min Act: -0.1700
Data Index: 7427898 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6203. Min Act: -0.1700
Data Index: 1172507 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.5881. Min Act: -0.1700
Data Index: 7079772 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0183. Min Range: -3.0183
Max Act: 2.6042. Min Act: -0.1700
Data Index: 1720810 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19