Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1690 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.9089. Min Act: -0.1700
Data Index: 335844 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.9089. Min Act: -0.1700
Data Index: 2359441 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.9089. Min Act: -0.1700
Data Index: 4863331 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.8464. Min Act: -0.1700
Data Index: 1231785 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.8151. Min Act: -0.1700
Data Index: 8424176 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.8151. Min Act: -0.1700
Data Index: 1804568 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.7526. Min Act: -0.1700
Data Index: 579529 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.7526. Min Act: -0.1700
Data Index: 5056430 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.7214. Min Act: -0.1700
Data Index: 5190567 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6901. Min Act: -0.1700
Data Index: 7958685 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6901. Min Act: -0.1700
Data Index: 4785923 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6589. Min Act: -0.1700
Data Index: 5243087 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6589. Min Act: -0.1700
Data Index: 6287847 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6589. Min Act: -0.1700
Data Index: 4593558 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6589. Min Act: -0.1700
Data Index: 1749264 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6276. Min Act: -0.1700
Data Index: 2218718 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6276. Min Act: -0.1700
Data Index: 3759457 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.6276. Min Act: -0.1700
Data Index: 8274976 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5964. Min Act: -0.1700
Data Index: 3794834 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9089. Min Range: -4.9089
Max Act: 4.5964. Min Act: -0.1700
Data Index: 6438882 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19