Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 353 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 1725685 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.8297. Min Act: -0.1700
Data Index: 7795027 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.6735. Min Act: -0.1700
Data Index: 5290944 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.6735. Min Act: -0.1700
Data Index: 5101062 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.6422. Min Act: -0.1700
Data Index: 3419235 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5797. Min Act: -0.1700
Data Index: 3298036 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5485. Min Act: -0.1700
Data Index: 8514390 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5485. Min Act: -0.1700
Data Index: 7175673 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5172. Min Act: -0.1700
Data Index: 7272258 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6756983 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5172. Min Act: -0.1700
Data Index: 4438181 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.5172. Min Act: -0.1700
Data Index: 6207737 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4860. Min Act: -0.1700
Data Index: 6499674 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4860. Min Act: -0.1700
Data Index: 4288953 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4860. Min Act: -0.1700
Data Index: 4825662 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4860. Min Act: -0.1700
Data Index: 3393353 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4860. Min Act: -0.1700
Data Index: 6065341 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4547. Min Act: -0.1700
Data Index: 8141804 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.3922. Min Act: -0.1700
Data Index: 821902 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8297. Min Range: -6.8297
Max Act: 6.4235. Min Act: -0.1700
Data Index: 5238162 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19