Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.4167. Min Act: -0.1700
Data Index: 4088437 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.3229. Min Act: -0.1700
Data Index: 2676930 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2917. Min Act: -0.1700
Data Index: 1141426 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2604. Min Act: -0.1700
Data Index: 3827001 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2604. Min Act: -0.1700
Data Index: 3936942 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2292. Min Act: -0.1700
Data Index: 6769112 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2292. Min Act: -0.1700
Data Index: 7418318 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.2292. Min Act: -0.1700
Data Index: 5726606 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1979. Min Act: -0.1700
Data Index: 4166860 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1979. Min Act: -0.1700
Data Index: 7882263 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1979. Min Act: -0.1700
Data Index: 8533556 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1667. Min Act: -0.1700
Data Index: 6769113 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1700
Data Index: 6703265 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1700
Data Index: 5964363 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1700
Data Index: 3567791 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1700
Data Index: 8142509 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1700
Data Index: 6703264 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1354. Min Act: -0.1696
Data Index: 7915638 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1042. Min Act: -0.1700
Data Index: 4732377 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4167. Min Range: -5.4167
Max Act: 5.1042. Min Act: -0.1700
Data Index: 7892021 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19