Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5165 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2099. Min Range: -7.2099
Max Act: 7.2099. Min Act: -0.1700
Data Index: 2170861 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2099. Min Range: -7.2099
Max Act: 7.1474. Min Act: -0.1700
Data Index: 124854 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2099. Min Range: -7.2099
Max Act: 7.1161. Min Act: -0.1700
Data Index: 4751632 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2099. Min Range: -7.2099
Max Act: 7.0536. Min Act: -0.1700
Data Index: 6271259 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.9911. Min Act: -0.1700
Data Index: 4736943 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.8661. Min Act: -0.1700
Data Index: 4317161 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.8661. Min Act: -0.1700
Data Index: 7074562 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.8349. Min Act: -0.1700
Data Index: 773604 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.7724. Min Act: -0.1700
Data Index: 4250200 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.7411. Min Act: -0.1700
Data Index: 5292947 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.7411. Min Act: -0.1700
Data Index: 2939798 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.7099. Min Act: -0.1700
Data Index: 5372792 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.7099. Min Act: -0.1700
Data Index: 4980640 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.6786. Min Act: -0.1700
Data Index: 5643533 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.6161. Min Act: -0.1700
Data Index: 4589585 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.6161. Min Act: -0.1700
Data Index: 7520869 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.6161. Min Act: -0.1700
Data Index: 537543 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.5849. Min Act: -0.1700
Data Index: 28301 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.5849. Min Act: -0.1700
Data Index: 3685058 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2099. Min Range: -7.2099
Max Act: 6.5849. Min Act: -0.1700
Data Index: 516198 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19