Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1832 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.2210. Min Act: -0.1700
Data Index: 7791349 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.2210. Min Act: -0.1700
Data Index: 462622 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.0960. Min Act: -0.1700
Data Index: 3489421 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.0647. Min Act: -0.1700
Data Index: 4565092 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.0647. Min Act: -0.1700
Data Index: 5752814 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9710. Min Act: -0.1700
Data Index: 2476813 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9710. Min Act: -0.1700
Data Index: 6267131 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2210. Min Range: -6.2210
Max Act: 6.0022. Min Act: -0.1700
Data Index: 7432475 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 5249117 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 3770836 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 1114771 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 3833376 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 6793180 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9397. Min Act: -0.1700
Data Index: 3513172 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5729274 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.8772. Min Act: -0.1700
Data Index: 8454950 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9085. Min Act: -0.1700
Data Index: 7095570 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.8772. Min Act: -0.1700
Data Index: 4964546 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.8772. Min Act: -0.1700
Data Index: 5727841 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2210. Min Range: -6.2210
Max Act: 5.9085. Min Act: -0.1700
Data Index: 5584446 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19