Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.8677. Min Act: -0.1700
Data Index: 3894891 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.6802. Min Act: -0.1700
Data Index: 6010282 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.6489. Min Act: -0.1700
Data Index: 8091908 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.6802. Min Act: -0.1700
Data Index: 742177 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.6177. Min Act: -0.1700
Data Index: 412519 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5864. Min Act: -0.1700
Data Index: 5612311 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5864. Min Act: -0.1700
Data Index: 7665073 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.6177. Min Act: -0.1700
Data Index: 6420145 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5552. Min Act: -0.1700
Data Index: 2316583 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5552. Min Act: -0.1700
Data Index: 3850862 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5239. Min Act: -0.1700
Data Index: 4112983 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5239. Min Act: -0.1700
Data Index: 8569383 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5239. Min Act: -0.1700
Data Index: 2625132 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.5239. Min Act: -0.1700
Data Index: 639479 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.4614. Min Act: -0.1700
Data Index: 2293231 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.4614. Min Act: -0.1700
Data Index: 4583293 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.4614. Min Act: -0.1700
Data Index: 7657704 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.4302. Min Act: -0.1700
Data Index: 1104337 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.3677. Min Act: -0.1700
Data Index: 1658782 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8677. Min Range: -6.8677
Max Act: 6.4302. Min Act: -0.1700
Data Index: 6719075 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #19