Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3519 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.7175. Min Act: -0.1700
Data Index: 2920935 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.6862. Min Act: -0.1700
Data Index: 6346912 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.5297. Min Act: -0.1700
Data Index: 1976862 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.5297. Min Act: -0.1700
Data Index: 7390704 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.5140. Min Act: -0.1700
Data Index: 5014430 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.5140. Min Act: -0.1700
Data Index: 725265 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4827. Min Act: -0.1700
Data Index: 6519908 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4827. Min Act: -0.1700
Data Index: 2072023 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4984. Min Act: -0.1700
Data Index: 1823732 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4827. Min Act: -0.1700
Data Index: 4502130 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4827. Min Act: -0.1700
Data Index: 2087913 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4671. Min Act: -0.1700
Data Index: 3185256 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4671. Min Act: -0.1700
Data Index: 976181 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4357. Min Act: -0.1700
Data Index: 5159593 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4357. Min Act: -0.1700
Data Index: 7621284 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4357. Min Act: -0.1700
Data Index: 3711070 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4200. Min Act: -0.1700
Data Index: 7670841 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4357. Min Act: -0.1700
Data Index: 7969226 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4044. Min Act: -0.1700
Data Index: 5427526 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7175. Min Range: -3.7175
Max Act: 3.4200. Min Act: -0.1700
Data Index: 308231 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #19