Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2826 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0915. Min Range: -6.0915
Max Act: 6.0915. Min Act: -0.1700
Data Index: 6660475 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0915. Min Range: -6.0915
Max Act: 6.0603. Min Act: -0.1700
Data Index: 8265862 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9978. Min Act: -0.1700
Data Index: 2333669 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0915. Min Range: -6.0915
Max Act: 6.0603. Min Act: -0.1700
Data Index: 6929636 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9978. Min Act: -0.1700
Data Index: 6621813 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9978. Min Act: -0.1700
Data Index: 8099083 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9353. Min Act: -0.1700
Data Index: 6579969 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9665. Min Act: -0.1700
Data Index: 7868972 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9353. Min Act: -0.1700
Data Index: 1025089 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9040. Min Act: -0.1700
Data Index: 6621815 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8728. Min Act: -0.1700
Data Index: 8099080 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8728. Min Act: -0.1700
Data Index: 4444142 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.9040. Min Act: -0.1700
Data Index: 8099082 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8415. Min Act: -0.1700
Data Index: 7658142 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8415. Min Act: -0.1700
Data Index: 6198661 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8103. Min Act: -0.1700
Data Index: 6621817 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8103. Min Act: -0.1700
Data Index: 1363600 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.8103. Min Act: -0.1700
Data Index: 4171598 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.7790. Min Act: -0.1700
Data Index: 2984232 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0915. Min Range: -6.0915
Max Act: 5.7790. Min Act: -0.1700
Data Index: 5788020 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19