Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3116 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0185. Min Range: -7.0185
Max Act: 7.0185. Min Act: -0.1700
Data Index: 4599387 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.8623. Min Act: -0.1700
Data Index: 5620288 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.7998. Min Act: -0.1700
Data Index: 1054235 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.7373. Min Act: -0.1700
Data Index: 3718006 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.7060. Min Act: -0.1700
Data Index: 3443309 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.6748. Min Act: -0.1700
Data Index: 6434726 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.6435. Min Act: -0.1700
Data Index: 1590261 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.6748. Min Act: -0.1700
Data Index: 5775314 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.6435. Min Act: -0.1700
Data Index: 1118082 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.6123. Min Act: -0.1700
Data Index: 3431763 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.5810. Min Act: -0.1700
Data Index: 4257584 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.5810. Min Act: -0.1700
Data Index: 3654842 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.5185. Min Act: -0.1700
Data Index: 3074639 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.4560. Min Act: -0.1700
Data Index: 5228671 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.3935. Min Act: -0.1700
Data Index: 3931750 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.3935. Min Act: -0.1700
Data Index: 1099849 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.4248. Min Act: -0.1700
Data Index: 2556968 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.3623. Min Act: -0.1700
Data Index: 2058026 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.3623. Min Act: -0.1700
Data Index: 4859322 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0185. Min Range: -7.0185
Max Act: 6.3623. Min Act: -0.1700
Data Index: 3906283 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #19