Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.5211. Min Range: -11.5211
Max Act: 11.5211. Min Act: -0.1700
Data Index: 1710639 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.5211. Min Range: -11.5211
Max Act: 11.2086. Min Act: -0.1700
Data Index: 8042961 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.5211. Min Range: -11.5211
Max Act: 11.0836. Min Act: -0.1700
Data Index: 1723313 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.5211. Min Range: -11.5211
Max Act: 11.0836. Min Act: -0.1700
Data Index: 4968224 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.5211. Min Range: -11.5211
Max Act: 11.0836. Min Act: -0.1700
Data Index: 4826363 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8961. Min Act: -0.1700
Data Index: 2027325 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.9586. Min Act: -0.1700
Data Index: 6674945 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8961. Min Act: -0.1700
Data Index: 5965999 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8961. Min Act: -0.1700
Data Index: 404836 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 6078417 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 3470890 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 5629218 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 4246002 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 2510225 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.8336. Min Act: -0.1700
Data Index: 6213053 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.7711. Min Act: -0.1700
Data Index: 1633433 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.7711. Min Act: -0.1700
Data Index: 91200 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.7711. Min Act: -0.1700
Data Index: 1851533 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.6461. Min Act: -0.1700
Data Index: 6130955 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.5211. Min Range: -11.5211
Max Act: 10.6461. Min Act: -0.1700
Data Index: 200219 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #19