Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.3994. Min Act: -0.1700
Data Index: 2359926 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.3524. Min Act: -0.1700
Data Index: 7539497 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.3210. Min Act: -0.1700
Data Index: 2862515 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.2110. Min Act: -0.1700
Data Index: 1094552 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1796. Min Act: -0.1700
Data Index: 8336611 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1953. Min Act: -0.1700
Data Index: 619099 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1796. Min Act: -0.1700
Data Index: 8004078 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1796. Min Act: -0.1700
Data Index: 2456109 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1481. Min Act: -0.1700
Data Index: 3126996 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1481. Min Act: -0.1700
Data Index: 1300078 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1324. Min Act: -0.1700
Data Index: 1198880 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.1166. Min Act: -0.1700
Data Index: 7940730 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0851. Min Act: -0.1700
Data Index: 226443 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0851. Min Act: -0.1700
Data Index: 7056097 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0693. Min Act: -0.1700
Data Index: 6675686 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0851. Min Act: -0.1700
Data Index: 1979546 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0535. Min Act: -0.1700
Data Index: 2987980 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0535. Min Act: -0.1700
Data Index: 5181881 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0378. Min Act: -0.1700
Data Index: 3613968 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3994. Min Range: -3.3994
Max Act: 3.0535. Min Act: -0.1700
Data Index: 1569860 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #19