Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4527 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.8057. Min Act: -0.1700
Data Index: 2885839 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.5557. Min Act: -0.1700
Data Index: 5501111 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.3682. Min Act: -0.1700
Data Index: 4767160 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.3057. Min Act: -0.1700
Data Index: 421874 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.2745. Min Act: -0.1700
Data Index: 5512672 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.2120. Min Act: -0.1700
Data Index: 411978 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.1807. Min Act: -0.1700
Data Index: 1221767 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.1495. Min Act: -0.1700
Data Index: 3176108 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.0870. Min Act: -0.1700
Data Index: 4389377 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.0557. Min Act: -0.1700
Data Index: 6892522 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.0245. Min Act: -0.1700
Data Index: 3883776 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8057. Min Range: -7.8057
Max Act: 7.0245. Min Act: -0.1700
Data Index: 5949103 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9932. Min Act: -0.1700
Data Index: 3957250 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9932. Min Act: -0.1700
Data Index: 356527 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9932. Min Act: -0.1700
Data Index: 3883753 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9620. Min Act: -0.1700
Data Index: 1531225 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9620. Min Act: -0.1700
Data Index: 4097788 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9620. Min Act: -0.1700
Data Index: 6776139 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9620. Min Act: -0.1700
Data Index: 726533 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8057. Min Range: -7.8057
Max Act: 6.9307. Min Act: -0.1700
Data Index: 3490216 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19