Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.8777. Min Act: -0.1700
Data Index: 5857540 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.7839. Min Act: -0.1700
Data Index: 3884834 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.7214. Min Act: -0.1700
Data Index: 5297314 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.6277. Min Act: -0.1700
Data Index: 7705985 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5964. Min Act: -0.1700
Data Index: 6810548 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.6277. Min Act: -0.1700
Data Index: 6583146 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5964. Min Act: -0.1700
Data Index: 1001189 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5964. Min Act: -0.1700
Data Index: 2764955 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5652. Min Act: -0.1700
Data Index: 6971652 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5652. Min Act: -0.1700
Data Index: 6437184 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5339. Min Act: -0.1700
Data Index: 2928620 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5339. Min Act: -0.1700
Data Index: 1626177 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5027. Min Act: -0.1700
Data Index: 3884814 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5339. Min Act: -0.1700
Data Index: 25543 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.5027. Min Act: -0.1700
Data Index: 2688527 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.4714. Min Act: -0.1700
Data Index: 1796881 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.4402. Min Act: -0.1700
Data Index: 3884811 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.4402. Min Act: -0.1700
Data Index: 257132 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.4089. Min Act: -0.1700
Data Index: 7051500 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8777. Min Range: -6.8777
Max Act: 6.4402. Min Act: -0.1700
Data Index: 4611492 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19