Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.6503. Min Act: -0.1700
Data Index: 7787290 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.4316. Min Act: -0.1700
Data Index: 797251 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.3691. Min Act: -0.1700
Data Index: 2288563 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.3691. Min Act: -0.1700
Data Index: 1647627 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.2441. Min Act: -0.1700
Data Index: 8530861 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.2128. Min Act: -0.1700
Data Index: 7947030 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.1191. Min Act: -0.1700
Data Index: 5505394 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.1503. Min Act: -0.1700
Data Index: 115676 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.1503. Min Act: -0.1700
Data Index: 7283306 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.0878. Min Act: -0.1700
Data Index: 3637113 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.0878. Min Act: -0.1700
Data Index: 4832850 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6503. Min Range: -7.6503
Max Act: 7.0253. Min Act: -0.1700
Data Index: 6393067 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9941. Min Act: -0.1700
Data Index: 1023691 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9941. Min Act: -0.1700
Data Index: 5447338 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9941. Min Act: -0.1700
Data Index: 2215923 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9628. Min Act: -0.1700
Data Index: 7569052 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9628. Min Act: -0.1700
Data Index: 3797008 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9316. Min Act: -0.1700
Data Index: 3000802 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9316. Min Act: -0.1700
Data Index: 6916578 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6503. Min Range: -7.6503
Max Act: 6.9316. Min Act: -0.1700
Data Index: 6478627 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19