Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.2796. Min Act: -0.1700
Data Index: 2802855 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.3109. Min Act: -0.1700
Data Index: 414623 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1859. Min Act: -0.1700
Data Index: 4107954 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1859. Min Act: -0.1700
Data Index: 5977214 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1546. Min Act: -0.1700
Data Index: 7495347 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1234. Min Act: -0.1700
Data Index: 435503 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1234. Min Act: -0.1700
Data Index: 6690192 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1234. Min Act: -0.1700
Data Index: 2802857 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.1234. Min Act: -0.1700
Data Index: 6944716 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.0921. Min Act: -0.1700
Data Index: 2802844 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.0608. Min Act: -0.1700
Data Index: 7208767 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.0608. Min Act: -0.1700
Data Index: 2047000 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.0608. Min Act: -0.1700
Data Index: 6945848 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3109. Min Range: -4.3109
Max Act: 4.0296. Min Act: -0.1700
Data Index: 3610623 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 1506631 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 3797663 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 5909678 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 4165751 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 7745507 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3109. Min Range: -4.3109
Max Act: 3.9983. Min Act: -0.1700
Data Index: 3606700 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19