Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3053 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.6504. Min Act: -0.1700
Data Index: 8009268 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.6816. Min Act: -0.1700
Data Index: 5950024 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1685608 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.6191. Min Act: -0.1700
Data Index: 1750117 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.5879. Min Act: -0.1700
Data Index: 4947736 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4941. Min Act: -0.1700
Data Index: 8358233 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4629. Min Act: -0.1700
Data Index: 1617636 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4316. Min Act: -0.1700
Data Index: 2901089 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4316. Min Act: -0.1700
Data Index: 8826865 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4316. Min Act: -0.1700
Data Index: 4244359 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4316. Min Act: -0.1700
Data Index: 1936714 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4004. Min Act: -0.1700
Data Index: 4685441 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4004. Min Act: -0.1700
Data Index: 3512286 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4316. Min Act: -0.1700
Data Index: 1119050 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4004. Min Act: -0.1700
Data Index: 1608185 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.4004. Min Act: -0.1700
Data Index: 8448543 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.3691. Min Act: -0.1700
Data Index: 3447325 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.3066. Min Act: -0.1700
Data Index: 5991007 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.3066. Min Act: -0.1700
Data Index: 6766414 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6816. Min Range: -5.6816
Max Act: 5.3066. Min Act: -0.1700
Data Index: 7198245 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19