Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2786. Min Range: -5.2786
Max Act: 5.2786. Min Act: -0.1700
Data Index: 8397327 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.4974. Min Act: -0.1700
Data Index: 439102 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.4661. Min Act: -0.1700
Data Index: 8106735 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.4974. Min Act: -0.1700
Data Index: 1418417 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.4349. Min Act: -0.1700
Data Index: 8183269 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.3724. Min Act: -0.1700
Data Index: 461072 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.3411. Min Act: -0.1700
Data Index: 990415 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.2786. Min Act: -0.1700
Data Index: 1749255 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.2474. Min Act: -0.1700
Data Index: 5769825 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.2474. Min Act: -0.1700
Data Index: 3142243 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.2161. Min Act: -0.1700
Data Index: 8106727 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.2161. Min Act: -0.1700
Data Index: 1022634 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1849. Min Act: -0.1700
Data Index: 2662866 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1536. Min Act: -0.1700
Data Index: 3470523 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1224. Min Act: -0.1700
Data Index: 616509 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1224. Min Act: -0.1700
Data Index: 7625875 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1536. Min Act: -0.1700
Data Index: 7474580 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1224. Min Act: -0.1700
Data Index: 1997160 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.1224. Min Act: -0.1700
Data Index: 7517280 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2786. Min Range: -5.2786
Max Act: 4.0911. Min Act: -0.1700
Data Index: 3006044 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #19