Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5363 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3136. Min Range: -9.3136
Max Act: 9.3136. Min Act: -0.1700
Data Index: 2752865 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3136. Min Range: -9.3136
Max Act: 9.1261. Min Act: -0.1700
Data Index: 6999257 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3136. Min Range: -9.3136
Max Act: 9.0636. Min Act: -0.1700
Data Index: 6808887 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3136. Min Range: -9.3136
Max Act: 9.0011. Min Act: -0.1700
Data Index: 759082 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.8761. Min Act: -0.1700
Data Index: 3401313 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.7511. Min Act: -0.1700
Data Index: 3361810 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.6886. Min Act: -0.1700
Data Index: 7668156 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.6261. Min Act: -0.1700
Data Index: 5274903 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.5636. Min Act: -0.1700
Data Index: 5388445 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 1917821 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.5011. Min Act: -0.1700
Data Index: 121459 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.4386. Min Act: -0.1700
Data Index: 6138603 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.4386. Min Act: -0.1700
Data Index: 6240130 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.3761. Min Act: -0.1700
Data Index: 2405268 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.4386. Min Act: -0.1700
Data Index: 5025411 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.4386. Min Act: -0.1700
Data Index: 852299 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.4386. Min Act: -0.1700
Data Index: 5303821 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.3761. Min Act: -0.1700
Data Index: 7681264 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.3761. Min Act: -0.1700
Data Index: 4446448 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3136. Min Range: -9.3136
Max Act: 8.3136. Min Act: -0.1700
Data Index: 4610182 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #19