Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4072. Min Range: -6.4072
Max Act: 6.4072. Min Act: -0.1700
Data Index: 7485369 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4072. Min Range: -6.4072
Max Act: 6.0947. Min Act: -0.1700
Data Index: 5926345 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4072. Min Range: -6.4072
Max Act: 6.1260. Min Act: -0.1700
Data Index: 2827992 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4072. Min Range: -6.4072
Max Act: 6.0635. Min Act: -0.1700
Data Index: 1083010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.9697. Min Act: -0.1700
Data Index: 2859606 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.9385. Min Act: -0.1700
Data Index: 8540877 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.9385. Min Act: -0.1700
Data Index: 6390648 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.9385. Min Act: -0.1700
Data Index: 3158896 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.9072. Min Act: -0.1700
Data Index: 3283315 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.8447. Min Act: -0.1700
Data Index: 5392851 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4288615 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.8135. Min Act: -0.1700
Data Index: 4267239 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 2437684 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 8446069 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 1549246 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6834771 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 3271805 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7510. Min Act: -0.1700
Data Index: 5010377 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7510. Min Act: -0.1700
Data Index: 7424373 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4072. Min Range: -6.4072
Max Act: 5.7822. Min Act: -0.1700
Data Index: 6117851 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19