Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3648 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8208975 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.3134. Min Act: -0.1700
Data Index: 8219815 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.2822. Min Act: -0.1700
Data Index: 4128124 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1884. Min Act: -0.1700
Data Index: 7536083 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1572. Min Act: -0.1700
Data Index: 3679216 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1259. Min Act: -0.1700
Data Index: 5551092 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1884. Min Act: -0.1700
Data Index: 7978704 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1259. Min Act: -0.1700
Data Index: 4596932 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1259. Min Act: -0.1700
Data Index: 1120282 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.1259. Min Act: -0.1700
Data Index: 8617064 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0947. Min Act: -0.1700
Data Index: 7353104 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0634. Min Act: -0.1700
Data Index: 8145409 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0634. Min Act: -0.1700
Data Index: 8349231 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0322. Min Act: -0.1700
Data Index: 3348171 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0634. Min Act: -0.1700
Data Index: 6470434 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0322. Min Act: -0.1700
Data Index: 7549634 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0322. Min Act: -0.1700
Data Index: 1938010 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0322. Min Act: -0.1700
Data Index: 3773498 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0009. Min Act: -0.1700
Data Index: 4149559 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3759. Min Range: -5.3759
Max Act: 5.0009. Min Act: -0.1700
Data Index: 1523060 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19