Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4703 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.5051. Min Act: -0.1700
Data Index: 8109582 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.2863. Min Act: -0.1700
Data Index: 6036593 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.2238. Min Act: -0.1700
Data Index: 2390764 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1926. Min Act: -0.1700
Data Index: 1592644 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1926. Min Act: -0.1700
Data Index: 6982868 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1926. Min Act: -0.1700
Data Index: 2672319 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1926. Min Act: -0.1700
Data Index: 3359018 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1613. Min Act: -0.1700
Data Index: 6036594 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1926. Min Act: -0.1700
Data Index: 1456965 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1613. Min Act: -0.1700
Data Index: 7537845 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1613. Min Act: -0.1700
Data Index: 8109583 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1301. Min Act: -0.1700
Data Index: 1220832 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1301. Min Act: -0.1700
Data Index: 6036600 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1301. Min Act: -0.1700
Data Index: 4970554 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.1301. Min Act: -0.1700
Data Index: 8589404 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.0988. Min Act: -0.1700
Data Index: 7537842 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.0675. Min Act: -0.1700
Data Index: 671147 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.0988. Min Act: -0.1700
Data Index: 7537850 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.0675. Min Act: -0.1700
Data Index: 1882073 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5051. Min Range: -4.5051
Max Act: 4.0675. Min Act: -0.1700
Data Index: 6982866 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19