Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4978 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.3470. Min Act: -0.1700
Data Index: 7880388 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.2845. Min Act: -0.1700
Data Index: 7190321 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.2845. Min Act: -0.1700
Data Index: 840761 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.2532. Min Act: -0.1700
Data Index: 4324622 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.2220. Min Act: -0.1700
Data Index: 4425731 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1907. Min Act: -0.1700
Data Index: 6773222 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1907. Min Act: -0.1700
Data Index: 6582828 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1907. Min Act: -0.1700
Data Index: 4209051 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1595. Min Act: -0.1700
Data Index: 1256942 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1595. Min Act: -0.1700
Data Index: 8829132 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1595. Min Act: -0.1700
Data Index: 1360243 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1282. Min Act: -0.1700
Data Index: 4506953 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0970. Min Act: -0.1700
Data Index: 440074 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1282. Min Act: -0.1700
Data Index: 5559641 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0970. Min Act: -0.1700
Data Index: 2967533 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0657. Min Act: -0.1700
Data Index: 8681798 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.1282. Min Act: -0.1700
Data Index: 8202053 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0970. Min Act: -0.1700
Data Index: 1865138 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0970. Min Act: -0.1700
Data Index: 7761057 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3470. Min Range: -4.3470
Max Act: 4.0970. Min Act: -0.1700
Data Index: 7174725 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19