Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2263 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.9093. Min Act: -0.1700
Data Index: 4070149 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.7843. Min Act: -0.1700
Data Index: 1364860 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.7530. Min Act: -0.1700
Data Index: 4707809 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6905. Min Act: -0.1700
Data Index: 4328 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6905. Min Act: -0.1700
Data Index: 6438684 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6905. Min Act: -0.1700
Data Index: 418871 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6280. Min Act: -0.1700
Data Index: 2868725 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6280. Min Act: -0.1700
Data Index: 6698212 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.6280. Min Act: -0.1700
Data Index: 7357214 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5968. Min Act: -0.1700
Data Index: 6193994 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5968. Min Act: -0.1700
Data Index: 797567 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5968. Min Act: -0.1700
Data Index: 5507540 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5968. Min Act: -0.1700
Data Index: 4529115 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5655. Min Act: -0.1700
Data Index: 4954381 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5655. Min Act: -0.1700
Data Index: 3615847 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5343. Min Act: -0.1700
Data Index: 7342702 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5030. Min Act: -0.1700
Data Index: 6483483 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5343. Min Act: -0.1700
Data Index: 3062794 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5030. Min Act: -0.1700
Data Index: 2568013 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9093. Min Range: -6.9093
Max Act: 6.5030. Min Act: -0.1700
Data Index: 5675700 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #19