Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4657 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.7622. Min Act: -0.1700
Data Index: 6329849 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.6059. Min Act: -0.1700
Data Index: 24331 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.2309. Min Act: -0.1700
Data Index: 389715 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.2309. Min Act: -0.1700
Data Index: 4364257 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.1684. Min Act: -0.1700
Data Index: 509095 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0746. Min Act: -0.1700
Data Index: 1638517 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0746. Min Act: -0.1700
Data Index: 5907511 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.1059. Min Act: -0.1700
Data Index: 1885827 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 1219182 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7660742 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7648398 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 7419599 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 6390289 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0434. Min Act: -0.1700
Data Index: 6642092 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7622. Min Range: -4.7622
Max Act: 4.0121. Min Act: -0.1700
Data Index: 7783977 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7622. Min Range: -4.7622
Max Act: 3.9808. Min Act: -0.1700
Data Index: 4513643 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7622. Min Range: -4.7622
Max Act: 3.9808. Min Act: -0.1700
Data Index: 2678325 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7622. Min Range: -4.7622
Max Act: 3.9808. Min Act: -0.1700
Data Index: 7080479 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7622. Min Range: -4.7622
Max Act: 3.9496. Min Act: -0.1700
Data Index: 4410731 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7622. Min Range: -4.7622
Max Act: 3.9808. Min Act: -0.1700
Data Index: 6472314 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #19