Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.4630. Min Act: -0.1700
Data Index: 1307641 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.3380. Min Act: -0.1700
Data Index: 2401047 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.3068. Min Act: -0.1700
Data Index: 6212179 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.2755. Min Act: -0.1700
Data Index: 5105064 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.2443. Min Act: -0.1700
Data Index: 111349 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.2130. Min Act: -0.1700
Data Index: 1303053 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.1818. Min Act: -0.1700
Data Index: 1457003 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.1505. Min Act: -0.1700
Data Index: 2265529 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 3677984 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 8027568 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0255. Min Act: -0.1700
Data Index: 3051537 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 523031 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 7709761 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 3891971 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4630. Min Range: -6.4630
Max Act: 6.0568. Min Act: -0.1700
Data Index: 7604375 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4630. Min Range: -6.4630
Max Act: 5.9943. Min Act: -0.1700
Data Index: 7562324 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4630. Min Range: -6.4630
Max Act: 5.9943. Min Act: -0.1700
Data Index: 4548094 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4630. Min Range: -6.4630
Max Act: 5.9630. Min Act: -0.1700
Data Index: 161008 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4630. Min Range: -6.4630
Max Act: 5.9630. Min Act: -0.1700
Data Index: 1108 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4630. Min Range: -6.4630
Max Act: 5.9318. Min Act: -0.1700
Data Index: 1785083 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #19