Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2872 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5805. Min Act: -0.1700
Data Index: 3050768 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5892. Min Act: -0.1700
Data Index: 8214516 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5718. Min Act: -0.1699
Data Index: 1580300 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5630. Min Act: -0.1700
Data Index: 3353768 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5543. Min Act: -0.1700
Data Index: 1865685 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5630. Min Act: -0.1700
Data Index: 517147 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5543. Min Act: -0.1700
Data Index: 4228664 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5455. Min Act: -0.1700
Data Index: 8295851 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5367. Min Act: -0.1700
Data Index: 6165814 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5367. Min Act: -0.1700
Data Index: 1567419 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5280. Min Act: -0.1700
Data Index: 5811390 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5192. Min Act: -0.1700
Data Index: 5381584 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5104. Min Act: -0.1700
Data Index: 6445416 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5192. Min Act: -0.1700
Data Index: 6871794 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5192. Min Act: -0.1700
Data Index: 506510 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5104. Min Act: -0.1697
Data Index: 6495779 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5104. Min Act: -0.1700
Data Index: 8076563 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5016. Min Act: -0.1700
Data Index: 2285607 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5016. Min Act: -0.1700
Data Index: 6139888 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5892. Min Range: -1.5892
Max Act: 1.5016. Min Act: -0.1698
Data Index: 6148954 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19