Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3040 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.7272. Min Act: -0.1700
Data Index: 2186047 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.6960. Min Act: -0.1700
Data Index: 3687713 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.6647. Min Act: -0.1700
Data Index: 848849 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.6022. Min Act: -0.1700
Data Index: 1636046 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.5710. Min Act: -0.1700
Data Index: 6067846 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.5085. Min Act: -0.1700
Data Index: 1952297 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.5085. Min Act: -0.1700
Data Index: 6611710 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.5085. Min Act: -0.1700
Data Index: 4891725 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.5085. Min Act: -0.1700
Data Index: 7667910 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4772. Min Act: -0.1700
Data Index: 785710 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4772. Min Act: -0.1700
Data Index: 3712473 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4772. Min Act: -0.1700
Data Index: 2323269 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4772. Min Act: -0.1700
Data Index: 8052128 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4460. Min Act: -0.1700
Data Index: 5121941 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4460. Min Act: -0.1700
Data Index: 788065 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4460. Min Act: -0.1700
Data Index: 2348849 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4147. Min Act: -0.1700
Data Index: 278520 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4147. Min Act: -0.1700
Data Index: 6898520 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4147. Min Act: -0.1700
Data Index: 4551999 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7272. Min Range: -6.7272
Max Act: 6.4147. Min Act: -0.1700
Data Index: 3782606 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19