Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3398 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2636. Min Range: -5.2636
Max Act: 5.2636. Min Act: -0.1700
Data Index: 6270316 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2636. Min Range: -5.2636
Max Act: 5.1074. Min Act: -0.1700
Data Index: 5789249 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2636. Min Range: -5.2636
Max Act: 5.0761. Min Act: -0.1700
Data Index: 276585 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2636. Min Range: -5.2636
Max Act: 5.0761. Min Act: -0.1700
Data Index: 6201788 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2636. Min Range: -5.2636
Max Act: 5.0761. Min Act: -0.1700
Data Index: 5292792 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.9824. Min Act: -0.1700
Data Index: 3607206 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.9824. Min Act: -0.1700
Data Index: 6567566 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.9824. Min Act: -0.1700
Data Index: 4349778 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.9511. Min Act: -0.1700
Data Index: 4649656 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.8886. Min Act: -0.1700
Data Index: 6623976 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.8886. Min Act: -0.1700
Data Index: 4555394 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.8261. Min Act: -0.1700
Data Index: 238191 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.8261. Min Act: -0.1700
Data Index: 8318487 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7949. Min Act: -0.1700
Data Index: 93703 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7949. Min Act: -0.1700
Data Index: 7648310 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7949. Min Act: -0.1700
Data Index: 3252149 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 2337018 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 3180974 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 627889 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2636. Min Range: -5.2636
Max Act: 4.7636. Min Act: -0.1700
Data Index: 6385940 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19