Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3090 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.7402. Min Act: -0.1700
Data Index: 1357496 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.6152. Min Act: -0.1700
Data Index: 2480593 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.6152. Min Act: -0.1700
Data Index: 6214901 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.4902. Min Act: -0.1700
Data Index: 2344184 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.4902. Min Act: -0.1700
Data Index: 258557 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.4277. Min Act: -0.1700
Data Index: 2398737 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3027. Min Act: -0.1700
Data Index: 3341143 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3652. Min Act: -0.1700
Data Index: 5155107 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3027. Min Act: -0.1700
Data Index: 7050056 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3027. Min Act: -0.1700
Data Index: 2995591 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3027. Min Act: -0.1700
Data Index: 3538487 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 138061 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.3027. Min Act: -0.1700
Data Index: 5549591 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 8472414 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 2382902 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 6133259 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.2402. Min Act: -0.1700
Data Index: 6324106 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.1777. Min Act: -0.1700
Data Index: 2521102 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.1777. Min Act: -0.1700
Data Index: 6686286 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7402. Min Range: -8.7402
Max Act: 8.1777. Min Act: -0.1700
Data Index: 2980710 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19