Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3313 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0067. Min Range: -6.0067
Max Act: 6.0067. Min Act: -0.1700
Data Index: 4277383 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.9442. Min Act: -0.1700
Data Index: 6677568 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.8192. Min Act: -0.1700
Data Index: 8560498 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.7880. Min Act: -0.1700
Data Index: 1951519 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.7880. Min Act: -0.1700
Data Index: 6848812 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.7255. Min Act: -0.1700
Data Index: 3513203 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.7255. Min Act: -0.1700
Data Index: 125110 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.7567. Min Act: -0.1700
Data Index: 1191685 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6942. Min Act: -0.1700
Data Index: 8127573 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6630. Min Act: -0.1700
Data Index: 3546928 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6317. Min Act: -0.1700
Data Index: 3562782 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6317. Min Act: -0.1700
Data Index: 5006232 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1347789 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6005. Min Act: -0.1700
Data Index: 7509284 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6005. Min Act: -0.1700
Data Index: 2075155 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1360745 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.6005. Min Act: -0.1700
Data Index: 1714834 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.5380. Min Act: -0.1700
Data Index: 3729373 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 1705359 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0067. Min Range: -6.0067
Max Act: 5.5692. Min Act: -0.1700
Data Index: 7823634 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19