Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3743 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.7554. Min Act: -0.1700
Data Index: 1181703 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.4116. Min Act: -0.1700
Data Index: 938054 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.3179. Min Act: -0.1700
Data Index: 8676574 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.2241. Min Act: -0.1700
Data Index: 6638701 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.1616. Min Act: -0.1700
Data Index: 7072911 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.1616. Min Act: -0.1700
Data Index: 2529349 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0991. Min Act: -0.1700
Data Index: 1567805 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0679. Min Act: -0.1700
Data Index: 8265303 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0366. Min Act: -0.1700
Data Index: 5609182 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0366. Min Act: -0.1700
Data Index: 591934 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0366. Min Act: -0.1700
Data Index: 8150730 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0366. Min Act: -0.1700
Data Index: 5487952 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0366. Min Act: -0.1700
Data Index: 8755266 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0054. Min Act: -0.1700
Data Index: 5609641 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0054. Min Act: -0.1700
Data Index: 1754019 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7554. Min Range: -6.7554
Max Act: 5.9741. Min Act: -0.1700
Data Index: 2586523 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7554. Min Range: -6.7554
Max Act: 5.9741. Min Act: -0.1700
Data Index: 7963153 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7554. Min Range: -6.7554
Max Act: 6.0054. Min Act: -0.1700
Data Index: 1083799 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7554. Min Range: -6.7554
Max Act: 5.9429. Min Act: -0.1700
Data Index: 6863620 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7554. Min Range: -6.7554
Max Act: 5.9741. Min Act: -0.1700
Data Index: 6717565 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #19