Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4151 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.3103. Min Act: -0.1700
Data Index: 7779114 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.2113. Min Act: -0.1700
Data Index: 3632958 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.2113. Min Act: -0.1700
Data Index: 4795273 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1947. Min Act: -0.1700
Data Index: 5817290 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1947. Min Act: -0.1700
Data Index: 4860652 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1947. Min Act: -0.1700
Data Index: 8747186 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1947. Min Act: -0.1700
Data Index: 842808 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1781. Min Act: -0.1700
Data Index: 5316826 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1781. Min Act: -0.1700
Data Index: 8463640 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1615. Min Act: -0.1700
Data Index: 5120149 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1615. Min Act: -0.1700
Data Index: 996525 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 7210469 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 3010734 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1281. Min Act: -0.1700
Data Index: 7537670 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1281. Min Act: -0.1700
Data Index: 5658213 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 7351314 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 1332312 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 3611481 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 2432510 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3103. Min Range: -2.3103
Max Act: 2.1448. Min Act: -0.1700
Data Index: 2326901 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19