Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2687 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1052. Min Range: -6.1052
Max Act: 6.1052. Min Act: -0.1700
Data Index: 5419092 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1052. Min Range: -6.1052
Max Act: 6.0740. Min Act: -0.1700
Data Index: 6063216 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1052. Min Range: -6.1052
Max Act: 6.0427. Min Act: -0.1700
Data Index: 7221174 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.9802. Min Act: -0.1700
Data Index: 5986718 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8865. Min Act: -0.1700
Data Index: 5986714 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8865. Min Act: -0.1700
Data Index: 7221175 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8552. Min Act: -0.1700
Data Index: 7221176 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8240. Min Act: -0.1700
Data Index: 2051211 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8552. Min Act: -0.1700
Data Index: 3212276 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.8240. Min Act: -0.1700
Data Index: 7221177 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.7615. Min Act: -0.1700
Data Index: 632055 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.7615. Min Act: -0.1700
Data Index: 4785061 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.7302. Min Act: -0.1700
Data Index: 1336309 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.7302. Min Act: -0.1700
Data Index: 8232006 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6990. Min Act: -0.1700
Data Index: 7434280 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6990. Min Act: -0.1700
Data Index: 144726 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6677. Min Act: -0.1700
Data Index: 2191167 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1692086 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6677. Min Act: -0.1700
Data Index: 1973582 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1052. Min Range: -6.1052
Max Act: 5.6677. Min Act: -0.1700
Data Index: 4739570 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #19