Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1331 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.9177. Min Act: -0.1700
Data Index: 5424991 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.7615. Min Act: -0.1700
Data Index: 8722516 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.6677. Min Act: -0.1700
Data Index: 7279925 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.6990. Min Act: -0.1700
Data Index: 8107163 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4802. Min Act: -0.1700
Data Index: 3502685 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.5115. Min Act: -0.1700
Data Index: 8564485 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.5427. Min Act: -0.1700
Data Index: 6747262 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4802. Min Act: -0.1700
Data Index: 5878614 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4802. Min Act: -0.1700
Data Index: 7152944 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4490. Min Act: -0.1700
Data Index: 7996554 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4490. Min Act: -0.1700
Data Index: 275711 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.4177. Min Act: -0.1700
Data Index: 5008480 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3865. Min Act: -0.1700
Data Index: 2060702 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3865. Min Act: -0.1700
Data Index: 6222426 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3865. Min Act: -0.1699
Data Index: 5819517 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3552. Min Act: -0.1700
Data Index: 5996116 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3552. Min Act: -0.1700
Data Index: 976367 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3552. Min Act: -0.1700
Data Index: 6990567 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.3552. Min Act: -0.1700
Data Index: 7025149 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9177. Min Range: -6.9177
Max Act: 6.2927. Min Act: -0.1700
Data Index: 8157572 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19