Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1256 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.8615. Min Act: -0.1700
Data Index: 8376535 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.5177. Min Act: -0.1700
Data Index: 4057920 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.5177. Min Act: -0.1700
Data Index: 5575781 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.4240. Min Act: -0.1700
Data Index: 4115096 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.2365. Min Act: -0.1700
Data Index: 6373365 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.2365. Min Act: -0.1700
Data Index: 1558189 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.2052. Min Act: -0.1700
Data Index: 3997839 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.1115. Min Act: -0.1700
Data Index: 4368264 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.1115. Min Act: -0.1700
Data Index: 2713441 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.0177. Min Act: -0.1700
Data Index: 7922000 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.0490. Min Act: -0.1700
Data Index: 86062 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.0177. Min Act: -0.1700
Data Index: 530794 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8615. Min Range: -7.8615
Max Act: 7.0177. Min Act: -0.1700
Data Index: 2374580 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 453698 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 7536849 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 6901717 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 4065421 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9865. Min Act: -0.1700
Data Index: 5477973 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9552. Min Act: -0.1700
Data Index: 2187165 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8615. Min Range: -7.8615
Max Act: 6.9552. Min Act: -0.1700
Data Index: 2372422 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #19