Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3569 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.6983. Min Act: -0.1700
Data Index: 3011560 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.5420. Min Act: -0.1700
Data Index: 5178028 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.4483. Min Act: -0.1700
Data Index: 3320713 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3858. Min Act: -0.1700
Data Index: 7682771 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3545. Min Act: -0.1700
Data Index: 3256144 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3545. Min Act: -0.1700
Data Index: 7402561 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7001498 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3233. Min Act: -0.1700
Data Index: 907966 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3233. Min Act: -0.1700
Data Index: 1935081 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7908486 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.3233. Min Act: -0.1700
Data Index: 7733748 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 5085322 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2608. Min Act: -0.1700
Data Index: 3266254 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2608. Min Act: -0.1700
Data Index: 5184795 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2608. Min Act: -0.1700
Data Index: 1437190 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 5692843 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 5830706 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 6001095 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 2661048 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6983. Min Range: -5.6983
Max Act: 5.2920. Min Act: -0.1700
Data Index: 7129704 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #19