Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.0480. Min Range: -6.0480
Max Act: 6.0480. Min Act: -0.1700
Data Index: 1693758 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0480. Min Range: -6.0480
Max Act: 6.0167. Min Act: -0.1700
Data Index: 5360793 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0480. Min Range: -6.0480
Max Act: 6.0167. Min Act: -0.1700
Data Index: 1309859 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.9855. Min Act: -0.1700
Data Index: 7495513 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.8605. Min Act: -0.1700
Data Index: 4903081 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.8292. Min Act: -0.1700
Data Index: 1082754 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.8292. Min Act: -0.1700
Data Index: 3930983 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.8292. Min Act: -0.1700
Data Index: 6657675 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 3947823 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7667. Min Act: -0.1700
Data Index: 6100622 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 5800858 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 3507938 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 6940159 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 2432074 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7355. Min Act: -0.1700
Data Index: 3778637 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7042. Min Act: -0.1700
Data Index: 7932451 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7042. Min Act: -0.1700
Data Index: 5765905 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7042. Min Act: -0.1700
Data Index: 6582915 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7042. Min Act: -0.1700
Data Index: 6951603 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0480. Min Range: -6.0480
Max Act: 5.7042. Min Act: -0.1700
Data Index: 7684710 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19