Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3202 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7709. Min Act: -0.1700
Data Index: 3503554 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7552. Min Act: -0.1700
Data Index: 1713671 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7552. Min Act: -0.1700
Data Index: 3468044 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.7083. Min Act: -0.1700
Data Index: 7070707 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6927. Min Act: -0.1700
Data Index: 7233128 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6144. Min Act: -0.1700
Data Index: 1715178 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.6144. Min Act: -0.1700
Data Index: 2973196 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 7038241 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 3468051 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 3633399 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5988. Min Act: -0.1700
Data Index: 3638112 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5675. Min Act: -0.1700
Data Index: 2775417 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 2682756 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 4998357 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 5213510 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5831. Min Act: -0.1700
Data Index: 3246645 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5675. Min Act: -0.1700
Data Index: 8437601 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5675. Min Act: -0.1700
Data Index: 3851467 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5675. Min Act: -0.1700
Data Index: 3468048 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7709. Min Range: -3.7709
Max Act: 3.5518. Min Act: -0.1700
Data Index: 4198724 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19