Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3453 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.1695. Min Act: -0.1700
Data Index: 8145879 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.1383. Min Act: -0.1700
Data Index: 1821140 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.1070. Min Act: -0.1700
Data Index: 6139823 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.0757. Min Act: -0.1700
Data Index: 7254769 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.1070. Min Act: -0.1700
Data Index: 1476366 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.0445. Min Act: -0.1700
Data Index: 2256909 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9976. Min Act: -0.1700
Data Index: 6507400 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1695. Min Range: -4.1695
Max Act: 4.0132. Min Act: -0.1700
Data Index: 16573 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9820. Min Act: -0.1700
Data Index: 5145206 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9351. Min Act: -0.1700
Data Index: 1664685 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9351. Min Act: -0.1700
Data Index: 3739278 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9351. Min Act: -0.1700
Data Index: 7620756 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9038. Min Act: -0.1700
Data Index: 4789096 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9038. Min Act: -0.1700
Data Index: 503886 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.9038. Min Act: -0.1700
Data Index: 5082410 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.8725. Min Act: -0.1700
Data Index: 1477823 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.8882. Min Act: -0.1700
Data Index: 3555944 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.8569. Min Act: -0.1700
Data Index: 3609908 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.8725. Min Act: -0.1700
Data Index: 1855617 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1695. Min Range: -4.1695
Max Act: 3.8725. Min Act: -0.1700
Data Index: 58143 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19