Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 13 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.5535. Min Act: -0.1700
Data Index: 690755 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.4910. Min Act: -0.1700
Data Index: 2361389 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.4285. Min Act: -0.1700
Data Index: 2637605 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.4285. Min Act: -0.1700
Data Index: 543867 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.3035. Min Act: -0.1700
Data Index: 8298150 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5535. Min Range: -8.5535
Max Act: 8.2410. Min Act: -0.1700
Data Index: 2644991 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.9910. Min Act: -0.1700
Data Index: 5869152 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.8972. Min Act: -0.1700
Data Index: 7396178 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.8972. Min Act: -0.1700
Data Index: 999257 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.8972. Min Act: -0.1700
Data Index: 36117 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 2590241 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 7785924 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7097. Min Act: -0.1700
Data Index: 7280328 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7722. Min Act: -0.1700
Data Index: 8052940 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7097. Min Act: -0.1700
Data Index: 2984698 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.7410. Min Act: -0.1700
Data Index: 274091 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.6785. Min Act: -0.1700
Data Index: 5525511 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.6160. Min Act: -0.1700
Data Index: 7280329 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.5847. Min Act: -0.1700
Data Index: 4710483 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5535. Min Range: -8.5535
Max Act: 7.5847. Min Act: -0.1700
Data Index: 2788864 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19