Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4984 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1510. Min Range: -7.1510
Max Act: 7.1510. Min Act: -0.1700
Data Index: 6050499 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.4322. Min Act: -0.1700
Data Index: 8716800 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.3697. Min Act: -0.1700
Data Index: 677985 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.3697. Min Act: -0.1700
Data Index: 6054898 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.3072. Min Act: -0.1700
Data Index: 3397171 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.2447. Min Act: -0.1700
Data Index: 7335853 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.2447. Min Act: -0.1700
Data Index: 8661174 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.2135. Min Act: -0.1700
Data Index: 3203529 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1822. Min Act: -0.1700
Data Index: 2766756 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1822. Min Act: -0.1700
Data Index: 1301458 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1510. Min Act: -0.1700
Data Index: 8372990 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1197. Min Act: -0.1700
Data Index: 4170036 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1510. Min Act: -0.1700
Data Index: 4619 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.1197. Min Act: -0.1700
Data Index: 5734880 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.0885. Min Act: -0.1700
Data Index: 2390775 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 2924879 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 5796596 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1510. Min Range: -7.1510
Max Act: 6.0572. Min Act: -0.1700
Data Index: 1175965 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1510. Min Range: -7.1510
Max Act: 5.9635. Min Act: -0.1700
Data Index: 4620578 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1510. Min Range: -7.1510
Max Act: 5.9947. Min Act: -0.1700
Data Index: 2849181 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19