Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1640 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.8491. Min Act: -0.1700
Data Index: 1444158 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.7866. Min Act: -0.1700
Data Index: 647599 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.6929. Min Act: -0.1700
Data Index: 4933872 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.6616. Min Act: -0.1700
Data Index: 1089257 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5991. Min Act: -0.1700
Data Index: 5155173 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5679. Min Act: -0.1700
Data Index: 8528284 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5679. Min Act: -0.1700
Data Index: 5334073 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5054. Min Act: -0.1700
Data Index: 6818010 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.4741. Min Act: -0.1700
Data Index: 6969920 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5054. Min Act: -0.1700
Data Index: 752786 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.5366. Min Act: -0.1700
Data Index: 2235889 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.4741. Min Act: -0.1700
Data Index: 7214091 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.4429. Min Act: -0.1700
Data Index: 5936458 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.4429. Min Act: -0.1700
Data Index: 7584532 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.3804. Min Act: -0.1700
Data Index: 152250 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.3179. Min Act: -0.1700
Data Index: 4851175 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.2866. Min Act: -0.1700
Data Index: 7598452 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.2866. Min Act: -0.1699
Data Index: 1117222 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.2241. Min Act: -0.1700
Data Index: 761085 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8491. Min Range: -6.8491
Max Act: 6.2554. Min Act: -0.1700
Data Index: 92345 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #19