Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3068 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.4480. Min Act: -0.1700
Data Index: 1778008 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.4167. Min Act: -0.1700
Data Index: 1040312 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.2292. Min Act: -0.1700
Data Index: 5866673 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.0730. Min Act: -0.1700
Data Index: 1111146 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.0417. Min Act: -0.1700
Data Index: 1841025 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9792. Min Act: -0.1700
Data Index: 1283081 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9480. Min Act: -0.1700
Data Index: 746898 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9792. Min Act: -0.1700
Data Index: 2736296 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9792. Min Act: -0.1700
Data Index: 3318441 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4480. Min Range: -6.4480
Max Act: 6.0105. Min Act: -0.1700
Data Index: 215002 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9480. Min Act: -0.1700
Data Index: 8534362 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9480. Min Act: -0.1700
Data Index: 4340811 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8855. Min Act: -0.1700
Data Index: 5092150 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.9167. Min Act: -0.1700
Data Index: 6003219 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8855. Min Act: -0.1700
Data Index: 7536499 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8855. Min Act: -0.1700
Data Index: 806301 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8230. Min Act: -0.1700
Data Index: 7754574 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8542. Min Act: -0.1700
Data Index: 6465117 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8542. Min Act: -0.1700
Data Index: 3335256 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4480. Min Range: -6.4480
Max Act: 5.8230. Min Act: -0.1700
Data Index: 4803234 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19