Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5629 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.3315. Min Act: -0.1700
Data Index: 7988332 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.3315. Min Act: -0.1700
Data Index: 7147664 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.3315. Min Act: -0.1700
Data Index: 1378589 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.1440. Min Act: -0.1700
Data Index: 3396653 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.1440. Min Act: -0.1700
Data Index: 1253601 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.1440. Min Act: -0.1700
Data Index: 1616500 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.1128. Min Act: -0.1700
Data Index: 5155657 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.0503. Min Act: -0.1700
Data Index: 1025957 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.0503. Min Act: -0.1700
Data Index: 1057672 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.0190. Min Act: -0.1700
Data Index: 5968281 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3315. Min Range: -7.3315
Max Act: 7.0190. Min Act: -0.1700
Data Index: 316041 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.9878. Min Act: -0.1700
Data Index: 4427913 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.9565. Min Act: -0.1700
Data Index: 5723757 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.9253. Min Act: -0.1700
Data Index: 2810620 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.9565. Min Act: -0.1700
Data Index: 2668216 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.8628. Min Act: -0.1700
Data Index: 7035958 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.8940. Min Act: -0.1700
Data Index: 4335265 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.8940. Min Act: -0.1700
Data Index: 2077501 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.8628. Min Act: -0.1700
Data Index: 4538946 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3315. Min Range: -7.3315
Max Act: 6.8628. Min Act: -0.1700
Data Index: 4769260 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19