Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5340 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2134. Min Range: -7.2134
Max Act: 7.2134. Min Act: -0.1700
Data Index: 1985887 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.9634. Min Act: -0.1700
Data Index: 2532988 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.9321. Min Act: -0.1700
Data Index: 84831 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.9321. Min Act: -0.1700
Data Index: 1160510 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.8696. Min Act: -0.1700
Data Index: 4002529 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.8384. Min Act: -0.1700
Data Index: 6126160 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.8384. Min Act: -0.1700
Data Index: 2351528 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.7446. Min Act: -0.1700
Data Index: 4995676 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.7446. Min Act: -0.1700
Data Index: 1018250 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6821. Min Act: -0.1700
Data Index: 4521587 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6821. Min Act: -0.1700
Data Index: 4383967 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6821. Min Act: -0.1700
Data Index: 8029554 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6821. Min Act: -0.1700
Data Index: 1212490 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6509. Min Act: -0.1700
Data Index: 541284 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6196. Min Act: -0.1700
Data Index: 1252236 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6196. Min Act: -0.1700
Data Index: 5792882 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6196. Min Act: -0.1700
Data Index: 6859894 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.5884. Min Act: -0.1700
Data Index: 2933148 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.5884. Min Act: -0.1700
Data Index: 3739981 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2134. Min Range: -7.2134
Max Act: 6.6196. Min Act: -0.1700
Data Index: 2433059 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19