Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3265 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.9967. Min Act: -0.1700
Data Index: 273012 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.8717. Min Act: -0.1700
Data Index: 5622216 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.3717. Min Act: -0.1700
Data Index: 8218897 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.1842. Min Act: -0.1700
Data Index: 1576448 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.1217. Min Act: -0.1700
Data Index: 4673731 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.1217. Min Act: -0.1700
Data Index: 6867896 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.0592. Min Act: -0.1700
Data Index: 2619696 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9967. Min Range: -9.9967
Max Act: 9.0592. Min Act: -0.1700
Data Index: 2909853 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.9967. Min Act: -0.1700
Data Index: 6596229 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.9967. Min Act: -0.1700
Data Index: 6270077 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.9967. Min Act: -0.1700
Data Index: 3350242 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.8717. Min Act: -0.1700
Data Index: 3571864 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.9342. Min Act: -0.1700
Data Index: 6836147 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.9342. Min Act: -0.1700
Data Index: 5514407 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.8092. Min Act: -0.1700
Data Index: 4645997 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.8717. Min Act: -0.1700
Data Index: 53269 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.8717. Min Act: -0.1700
Data Index: 8193201 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.7467. Min Act: -0.1700
Data Index: 4679160 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.8092. Min Act: -0.1700
Data Index: 6368107 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9967. Min Range: -9.9967
Max Act: 8.7467. Min Act: -0.1700
Data Index: 2659101 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #19