Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1821 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.3673. Min Act: -0.1700
Data Index: 4603891 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.3346. Min Act: -0.1700
Data Index: 6806108 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1694. Min Act: -0.1700
Data Index: 4361200 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1694. Min Act: -0.1700
Data Index: 7391671 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1694. Min Act: -0.1700
Data Index: 6295034 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1527. Min Act: -0.1700
Data Index: 7211239 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1527. Min Act: -0.1700
Data Index: 7075390 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1527. Min Act: -0.1700
Data Index: 589292 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1193. Min Act: -0.1700
Data Index: 6383219 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1361. Min Act: -0.1700
Data Index: 5838957 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1361. Min Act: -0.1700
Data Index: 3446247 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1193. Min Act: -0.1700
Data Index: 3344815 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1193. Min Act: -0.1700
Data Index: 7565315 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1193. Min Act: -0.1700
Data Index: 7211232 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1026. Min Act: -0.1700
Data Index: 8378908 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1026. Min Act: -0.1700
Data Index: 6948472 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.0859. Min Act: -0.1700
Data Index: 528022 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.1026. Min Act: -0.1700
Data Index: 2689176 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.0859. Min Act: -0.1700
Data Index: 3478413 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3673. Min Range: -2.3673
Max Act: 2.0859. Min Act: -0.1700
Data Index: 2689177 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #19