Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.7969. Min Act: -0.1700
Data Index: 2838380 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.7969. Min Act: -0.1700
Data Index: 8121552 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.6719. Min Act: -0.1700
Data Index: 908949 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.6094. Min Act: -0.1700
Data Index: 8699636 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.6719. Min Act: -0.1700
Data Index: 365333 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.6094. Min Act: -0.1700
Data Index: 986792 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.6094. Min Act: -0.1700
Data Index: 2410964 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.5469. Min Act: -0.1700
Data Index: 5477627 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 897978 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 188449 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 4561288 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 568245 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 4825860 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4844. Min Act: -0.1700
Data Index: 5331832 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4219. Min Act: -0.1700
Data Index: 5914954 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4219. Min Act: -0.1700
Data Index: 7702399 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4219. Min Act: -0.1700
Data Index: 5547384 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.4219. Min Act: -0.1700
Data Index: 4378242 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.3594. Min Act: -0.1700
Data Index: 583510 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7969. Min Range: -8.7969
Max Act: 8.3594. Min Act: -0.1700
Data Index: 6600659 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19