Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5061 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.4193. Min Act: -0.1700
Data Index: 6511603 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.4193. Min Act: -0.1700
Data Index: 8755722 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3879. Min Act: -0.1700
Data Index: 4256270 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3879. Min Act: -0.1700
Data Index: 263142 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3879. Min Act: -0.1700
Data Index: 2246338 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3722. Min Act: -0.1700
Data Index: 2825421 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3566. Min Act: -0.1700
Data Index: 1446524 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3409. Min Act: -0.1700
Data Index: 1830610 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3566. Min Act: -0.1700
Data Index: 5217042 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3566. Min Act: -0.1700
Data Index: 6118658 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3409. Min Act: -0.1700
Data Index: 4592343 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3252. Min Act: -0.1700
Data Index: 6874188 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3252. Min Act: -0.1700
Data Index: 7585819 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3252. Min Act: -0.1700
Data Index: 1384446 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3095. Min Act: -0.1700
Data Index: 1230669 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.3095. Min Act: -0.1700
Data Index: 8176080 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.2938. Min Act: -0.1700
Data Index: 6753852 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.2938. Min Act: -0.1700
Data Index: 3602083 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.2938. Min Act: -0.1700
Data Index: 3456403 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4193. Min Range: -3.4193
Max Act: 3.2938. Min Act: -0.1700
Data Index: 6753849 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19