Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0021. Min Range: -6.0021
Max Act: 6.0021. Min Act: -0.1700
Data Index: 5763969 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0021. Min Range: -6.0021
Max Act: 6.0021. Min Act: -0.1700
Data Index: 758277 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.9084. Min Act: -0.1700
Data Index: 3667177 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.9084. Min Act: -0.1700
Data Index: 2051656 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.8771. Min Act: -0.1700
Data Index: 123538 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.9084. Min Act: -0.1700
Data Index: 4902816 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.8459. Min Act: -0.1700
Data Index: 8286589 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.8459. Min Act: -0.1700
Data Index: 5555538 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7834. Min Act: -0.1700
Data Index: 945116 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.8459. Min Act: -0.1700
Data Index: 1537472 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.8146. Min Act: -0.1700
Data Index: 429528 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7834. Min Act: -0.1700
Data Index: 6391543 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7834. Min Act: -0.1700
Data Index: 5856966 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7521. Min Act: -0.1700
Data Index: 3267334 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7209. Min Act: -0.1700
Data Index: 710080 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.6896. Min Act: -0.1700
Data Index: 5389648 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.6896. Min Act: -0.1700
Data Index: 3526493 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.6896. Min Act: -0.1700
Data Index: 1669995 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.7209. Min Act: -0.1700
Data Index: 4335307 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0021. Min Range: -6.0021
Max Act: 5.6896. Min Act: -0.1700
Data Index: 4563698 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19