Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4382 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.5267. Min Act: -0.1700
Data Index: 3071067 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.4456. Min Act: -0.1700
Data Index: 3810967 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.4294. Min Act: -0.1700
Data Index: 818291 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3967. Min Act: -0.1700
Data Index: 4093475 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3967. Min Act: -0.1700
Data Index: 3951607 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3804. Min Act: -0.1700
Data Index: 4958613 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3804. Min Act: -0.1700
Data Index: 8792682 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3641. Min Act: -0.1699
Data Index: 8792680 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3477. Min Act: -0.1700
Data Index: 1669188 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3641. Min Act: -0.1700
Data Index: 5003271 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3641. Min Act: -0.1700
Data Index: 3661289 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3313. Min Act: -0.1700
Data Index: 4650733 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3477. Min Act: -0.1700
Data Index: 3528639 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3641. Min Act: -0.1700
Data Index: 7226283 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3477. Min Act: -0.1700
Data Index: 913694 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3313. Min Act: -0.1700
Data Index: 1169587 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3149. Min Act: -0.1700
Data Index: 1945217 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3313. Min Act: -0.1700
Data Index: 2316580 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3313. Min Act: -0.1700
Data Index: 293251 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5267. Min Range: -2.5267
Max Act: 2.3313. Min Act: -0.1700
Data Index: 1329701 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19