Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.3021. Min Act: -0.1700
Data Index: 1847294 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3021. Min Range: -6.3021
Max Act: 6.0209. Min Act: -0.1700
Data Index: 3362073 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.9584. Min Act: -0.1700
Data Index: 3962278 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.9584. Min Act: -0.1700
Data Index: 684377 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8959. Min Act: -0.1700
Data Index: 135957 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8959. Min Act: -0.1700
Data Index: 135953 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7662929 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8334. Min Act: -0.1700
Data Index: 7244394 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8021. Min Act: -0.1700
Data Index: 5530059 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7709. Min Act: -0.1700
Data Index: 1156645 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.8021. Min Act: -0.1700
Data Index: 6010361 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7709. Min Act: -0.1700
Data Index: 790493 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 2682794 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7396. Min Act: -0.1700
Data Index: 7160213 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 5730244 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7145843 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 2883015 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.6771. Min Act: -0.1700
Data Index: 3410021 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 4304591 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3021. Min Range: -6.3021
Max Act: 5.7084. Min Act: -0.1700
Data Index: 7589324 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19