Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3029 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.3964. Min Act: -0.1700
Data Index: 4917074 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.3652. Min Act: -0.1700
Data Index: 5946990 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.3339. Min Act: -0.1700
Data Index: 6300975 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.3339. Min Act: -0.1700
Data Index: 1571883 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.3027. Min Act: -0.1700
Data Index: 8053022 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.2714. Min Act: -0.1700
Data Index: 848203 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.2402. Min Act: -0.1700
Data Index: 356150 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 1447907 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1777. Min Act: -0.1700
Data Index: 244185 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1464. Min Act: -0.1700
Data Index: 409967 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1464. Min Act: -0.1700
Data Index: 5928513 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1152. Min Act: -0.1700
Data Index: 707827 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.1152. Min Act: -0.1700
Data Index: 4882861 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0839. Min Act: -0.1700
Data Index: 7406061 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0839. Min Act: -0.1700
Data Index: 77876 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0527. Min Act: -0.1700
Data Index: 3591156 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0214. Min Act: -0.1700
Data Index: 534021 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0527. Min Act: -0.1700
Data Index: 8406351 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0527. Min Act: -0.1700
Data Index: 8006529 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3964. Min Range: -6.3964
Max Act: 6.0214. Min Act: -0.1700
Data Index: 5178752 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19