Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3082 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.3755. Min Act: -0.1700
Data Index: 2554218 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2970. Min Act: -0.1700
Data Index: 2344261 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2970. Min Act: -0.1700
Data Index: 2749101 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2656. Min Act: -0.1700
Data Index: 819794 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2656. Min Act: -0.1700
Data Index: 325641 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2499. Min Act: -0.1700
Data Index: 820940 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2970. Min Act: -0.1700
Data Index: 3018093 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2499. Min Act: -0.1700
Data Index: 6739439 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2342. Min Act: -0.1700
Data Index: 4687854 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2499. Min Act: -0.1700
Data Index: 7476203 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2342. Min Act: -0.1700
Data Index: 6584533 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2185. Min Act: -0.1700
Data Index: 6798017 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2028. Min Act: -0.1700
Data Index: 3064626 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2185. Min Act: -0.1700
Data Index: 7172308 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2185. Min Act: -0.1700
Data Index: 5687532 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2028. Min Act: -0.1700
Data Index: 8453634 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2028. Min Act: -0.1700
Data Index: 4746057 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2028. Min Act: -0.1700
Data Index: 4051232 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.2028. Min Act: -0.1700
Data Index: 4934171 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3755. Min Range: -3.3755
Max Act: 3.1870. Min Act: -0.1700
Data Index: 7945661 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19