Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5525 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2884. Min Range: -9.2884
Max Act: 9.2884. Min Act: -0.1700
Data Index: 7426251 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2884. Min Range: -9.2884
Max Act: 9.2884. Min Act: -0.1700
Data Index: 722752 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2884. Min Range: -9.2884
Max Act: 9.1009. Min Act: -0.1700
Data Index: 72500 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.9759. Min Act: -0.1700
Data Index: 5998343 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.9134. Min Act: -0.1700
Data Index: 3538393 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.9134. Min Act: -0.1700
Data Index: 2988812 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.8509. Min Act: -0.1700
Data Index: 8087065 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.7259. Min Act: -0.1700
Data Index: 5317267 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6634. Min Act: -0.1700
Data Index: 6619382 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6009. Min Act: -0.1700
Data Index: 3365112 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6009. Min Act: -0.1700
Data Index: 5768656 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6009. Min Act: -0.1700
Data Index: 2348355 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6009. Min Act: -0.1700
Data Index: 8745656 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.5384. Min Act: -0.1700
Data Index: 4907809 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.6009. Min Act: -0.1700
Data Index: 1781539 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.4759. Min Act: -0.1700
Data Index: 7918935 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.4759. Min Act: -0.1700
Data Index: 8747931 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.3509. Min Act: -0.1700
Data Index: 6384175 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.4134. Min Act: -0.1700
Data Index: 3804338 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2884. Min Range: -9.2884
Max Act: 8.4134. Min Act: -0.1700
Data Index: 7731578 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19