Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6329 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.7147. Min Act: -0.1700
Data Index: 599266 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6991. Min Act: -0.1700
Data Index: 4259216 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6522. Min Act: -0.1700
Data Index: 6766956 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 7506473 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 2846159 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 7055680 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.6209. Min Act: -0.1700
Data Index: 6518373 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5739. Min Act: -0.1700
Data Index: 320286 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 3821358 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5739. Min Act: -0.1700
Data Index: 15550 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5583. Min Act: -0.1700
Data Index: 6968811 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5896. Min Act: -0.1700
Data Index: 7655167 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5583. Min Act: -0.1700
Data Index: 5273024 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5426. Min Act: -0.1700
Data Index: 538978 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5426. Min Act: -0.1700
Data Index: 4689554 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5270. Min Act: -0.1700
Data Index: 6786278 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.5270. Min Act: -0.1700
Data Index: 906413 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.4956. Min Act: -0.1700
Data Index: 1591301 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.4956. Min Act: -0.1700
Data Index: 5906939 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7147. Min Range: -3.7147
Max Act: 3.4956. Min Act: -0.1700
Data Index: 5938063 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #19