Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4897. Min Act: -0.1700
Data Index: 5233179 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4897. Min Act: -0.1700
Data Index: 1474410 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4897. Min Act: -0.1700
Data Index: 5988822 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4897. Min Act: -0.1700
Data Index: 2568370 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4585. Min Act: -0.1700
Data Index: 7397574 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4272. Min Act: -0.1700
Data Index: 745701 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4585. Min Act: -0.1700
Data Index: 6917188 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.3647. Min Act: -0.1700
Data Index: 1624792 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4272. Min Act: -0.1700
Data Index: 7601534 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.4272. Min Act: -0.1700
Data Index: 3560489 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.3647. Min Act: -0.1700
Data Index: 3117590 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.3022. Min Act: -0.1700
Data Index: 8047821 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.3022. Min Act: -0.1700
Data Index: 2322193 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1772. Min Act: -0.1700
Data Index: 1222517 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1460. Min Act: -0.1700
Data Index: 3948286 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1147. Min Act: -0.1700
Data Index: 4345095 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1147. Min Act: -0.1700
Data Index: 6892792 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1147. Min Act: -0.1700
Data Index: 3821657 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1460. Min Act: -0.1700
Data Index: 5934116 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4897. Min Range: -4.4897
Max Act: 4.1147. Min Act: -0.1700
Data Index: 5519095 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19