Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1629. Min Range: -2.1629
Max Act: 2.1629. Min Act: -0.1700
Data Index: 3714453 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1629. Min Range: -2.1629
Max Act: 2.0457. Min Act: -0.1700
Data Index: 3714456 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1629. Min Range: -2.1629
Max Act: 2.0457. Min Act: -0.1700
Data Index: 2214239 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9951. Min Act: -0.1700
Data Index: 115949 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9951. Min Act: -0.1700
Data Index: 8207352 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9951. Min Act: -0.1700
Data Index: 2214238 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9613. Min Act: -0.1700
Data Index: 8207354 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9443. Min Act: -0.1700
Data Index: 2214243 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9443. Min Act: -0.1700
Data Index: 8207353 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9443. Min Act: -0.1700
Data Index: 8207356 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9273. Min Act: -0.1700
Data Index: 3714452 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9273. Min Act: -0.1700
Data Index: 3714455 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.9273. Min Act: -0.1700
Data Index: 3714454 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8932. Min Act: -0.1700
Data Index: 3714450 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8932. Min Act: -0.1700
Data Index: 6795610 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8932. Min Act: -0.1700
Data Index: 8207351 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8761. Min Act: -0.1700
Data Index: 6795614 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8590. Min Act: -0.1700
Data Index: 8207355 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8761. Min Act: -0.1700
Data Index: 2214237 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1629. Min Range: -2.1629
Max Act: 1.8419. Min Act: -0.1700
Data Index: 6679153 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #19