Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4304 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3373. Min Range: -9.3373
Max Act: 9.3373. Min Act: -0.1700
Data Index: 3585682 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.8998. Min Act: -0.1700
Data Index: 8649212 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.7123. Min Act: -0.1700
Data Index: 1410452 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.7123. Min Act: -0.1700
Data Index: 4374748 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.5248. Min Act: -0.1700
Data Index: 826293 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.5248. Min Act: -0.1700
Data Index: 6105939 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.4623. Min Act: -0.1700
Data Index: 4120719 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.4623. Min Act: -0.1700
Data Index: 1433531 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.3998. Min Act: -0.1700
Data Index: 1257225 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.4623. Min Act: -0.1700
Data Index: 5227713 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.3998. Min Act: -0.1700
Data Index: 4349745 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.3998. Min Act: -0.1700
Data Index: 7613257 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.3373. Min Act: -0.1700
Data Index: 6969958 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.3373. Min Act: -0.1700
Data Index: 3311600 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.2748. Min Act: -0.1700
Data Index: 548099 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.2123. Min Act: -0.1700
Data Index: 5926719 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.2123. Min Act: -0.1700
Data Index: 2829245 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.2123. Min Act: -0.1700
Data Index: 470912 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.2123. Min Act: -0.1700
Data Index: 4643706 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3373. Min Range: -9.3373
Max Act: 8.1498. Min Act: -0.1700
Data Index: 5864793 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #19