Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1319 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.5595. Min Act: -0.1700
Data Index: 15428 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.4345. Min Act: -0.1700
Data Index: 5800177 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.4033. Min Act: -0.1700
Data Index: 7561404 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.4033. Min Act: -0.1700
Data Index: 670743 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5283409 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3720. Min Act: -0.1700
Data Index: 8639885 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3720. Min Act: -0.1700
Data Index: 5007739 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4820879 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3720. Min Act: -0.1700
Data Index: 4315466 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.4033. Min Act: -0.1700
Data Index: 5750543 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.3408. Min Act: -0.1700
Data Index: 4709059 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 8608538 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 1942984 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 4067563 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 6537452 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 7492786 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2783. Min Act: -0.1700
Data Index: 5321021 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2470. Min Act: -0.1700
Data Index: 6889000 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2470. Min Act: -0.1700
Data Index: 4164329 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5595. Min Range: -5.5595
Max Act: 5.2470. Min Act: -0.1700
Data Index: 8502023 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19