Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2937 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.5228. Min Act: -0.1700
Data Index: 7039108 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.4417. Min Act: -0.1700
Data Index: 644526 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.4091. Min Act: -0.1700
Data Index: 7300375 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.4254. Min Act: -0.1700
Data Index: 1216870 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3928. Min Act: -0.1700
Data Index: 7683375 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3928. Min Act: -0.1700
Data Index: 2191330 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3928. Min Act: -0.1700
Data Index: 5977131 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.4091. Min Act: -0.1700
Data Index: 5281599 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3273. Min Act: -0.1700
Data Index: 4966893 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3273. Min Act: -0.1700
Data Index: 2010586 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3273. Min Act: -0.1699
Data Index: 7912142 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3273. Min Act: -0.1700
Data Index: 7318245 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3109. Min Act: -0.1700
Data Index: 7528748 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3273. Min Act: -0.1700
Data Index: 8079781 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.2945. Min Act: -0.1700
Data Index: 7624187 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3109. Min Act: -0.1700
Data Index: 2003525 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.2945. Min Act: -0.1700
Data Index: 3841854 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.3109. Min Act: -0.1700
Data Index: 7198544 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.2945. Min Act: -0.1700
Data Index: 6759482 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5228. Min Range: -2.5228
Max Act: 2.2945. Min Act: -0.1700
Data Index: 482884 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19