Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2294 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.3514. Min Act: -0.1700
Data Index: 1955811 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.3514. Min Act: -0.1700
Data Index: 1836969 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.2889. Min Act: -0.1700
Data Index: 2814074 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.2889. Min Act: -0.1700
Data Index: 1682912 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.2264. Min Act: -0.1700
Data Index: 2897995 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.1639. Min Act: -0.1700
Data Index: 7712086 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.2264. Min Act: -0.1700
Data Index: 3373876 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.2264. Min Act: -0.1700
Data Index: 8615036 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.1014. Min Act: -0.1700
Data Index: 7174706 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.1014. Min Act: -0.1700
Data Index: 2971931 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 3607273 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 5679309 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 4745333 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 6290064 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 5860946 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3514. Min Range: -9.3514
Max Act: 9.0389. Min Act: -0.1700
Data Index: 3783760 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3514. Min Range: -9.3514
Max Act: 8.9764. Min Act: -0.1700
Data Index: 1771598 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3514. Min Range: -9.3514
Max Act: 8.9764. Min Act: -0.1700
Data Index: 3509553 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3514. Min Range: -9.3514
Max Act: 8.9139. Min Act: -0.1700
Data Index: 5444226 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3514. Min Range: -9.3514
Max Act: 8.9139. Min Act: -0.1700
Data Index: 5680438 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19