Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.7543. Min Act: -0.1700
Data Index: 2553565 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.6918. Min Act: -0.1700
Data Index: 4665432 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 3367609 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.4418. Min Act: -0.1700
Data Index: 1418602 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 3758550 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.4418. Min Act: -0.1700
Data Index: 4223575 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.3793. Min Act: -0.1700
Data Index: 4246338 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.2543. Min Act: -0.1700
Data Index: 1094161 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.2543. Min Act: -0.1700
Data Index: 4059105 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 7314078 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 7338679 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 3158172 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 1683742 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 3579068 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 4778823 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 7523582 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 3499190 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 6354851 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1918. Min Act: -0.1700
Data Index: 4726247 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7543. Min Range: -9.7543
Max Act: 9.1293. Min Act: -0.1700
Data Index: 5739507 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19