Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4133. Min Range: -7.4133
Max Act: 7.4133. Min Act: -0.1700
Data Index: 7793043 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.9445. Min Act: -0.1700
Data Index: 6306098 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.9133. Min Act: -0.1700
Data Index: 3197121 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.8820. Min Act: -0.1700
Data Index: 4407502 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.8195. Min Act: -0.1700
Data Index: 6942797 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.7258. Min Act: -0.1700
Data Index: 6824640 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.6945. Min Act: -0.1700
Data Index: 4518675 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.6008. Min Act: -0.1700
Data Index: 6099084 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5695. Min Act: -0.1700
Data Index: 1755413 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.6008. Min Act: -0.1700
Data Index: 7065775 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.6008. Min Act: -0.1700
Data Index: 7232879 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5383. Min Act: -0.1700
Data Index: 2584507 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.4758. Min Act: -0.1700
Data Index: 3537951 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5070. Min Act: -0.1700
Data Index: 4519006 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5070. Min Act: -0.1700
Data Index: 191140 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5070. Min Act: -0.1700
Data Index: 6824641 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.5070. Min Act: -0.1700
Data Index: 3701467 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.4758. Min Act: -0.1700
Data Index: 5229387 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.4758. Min Act: -0.1700
Data Index: 7162472 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4133. Min Range: -7.4133
Max Act: 6.4445. Min Act: -0.1700
Data Index: 3307906 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19