Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0158. Min Range: -5.0158
Max Act: 5.0158. Min Act: -0.1700
Data Index: 3874599 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.6408. Min Act: -0.1700
Data Index: 964716 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.6095. Min Act: -0.1700
Data Index: 7654244 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.5783. Min Act: -0.1700
Data Index: 6387914 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.5470. Min Act: -0.1700
Data Index: 362229 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.5158. Min Act: -0.1700
Data Index: 7247310 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.5158. Min Act: -0.1700
Data Index: 7977432 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4845. Min Act: -0.1700
Data Index: 362220 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4845. Min Act: -0.1700
Data Index: 5718885 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 687946 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4845. Min Act: -0.1700
Data Index: 2149421 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 5693439 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 1263290 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 2502703 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 7409288 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 5273700 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 4982846 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.4533. Min Act: -0.1700
Data Index: 7558454 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.3908. Min Act: -0.1700
Data Index: 537633 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0158. Min Range: -5.0158
Max Act: 4.3908. Min Act: -0.1700
Data Index: 2796312 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19