Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1251 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4667. Min Act: -0.1700
Data Index: 4327233 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4667. Min Act: -0.1700
Data Index: 4327232 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.4042. Min Act: -0.1700
Data Index: 8278161 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.3104. Min Act: -0.1700
Data Index: 5564122 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 4670233 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2792. Min Act: -0.1700
Data Index: 6613374 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 5009547 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 5973786 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2479. Min Act: -0.1700
Data Index: 1932092 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.2166. Min Act: -0.1700
Data Index: 8447730 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1854. Min Act: -0.1700
Data Index: 7349209 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 1389047 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 2788476 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 219139 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 3581303 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 7627753 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 7924354 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.1541. Min Act: -0.1700
Data Index: 6620252 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0916. Min Act: -0.1700
Data Index: 3631838 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4667. Min Range: -4.4667
Max Act: 4.0916. Min Act: -0.1700
Data Index: 5961786 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19