Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3560 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2389. Min Range: -8.2389
Max Act: 8.2389. Min Act: -0.1700
Data Index: 8315666 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2389. Min Range: -8.2389
Max Act: 8.1139. Min Act: -0.1700
Data Index: 558963 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2389. Min Range: -8.2389
Max Act: 8.0827. Min Act: -0.1700
Data Index: 5507347 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.9889. Min Act: -0.1700
Data Index: 2964960 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.9577. Min Act: -0.1700
Data Index: 558964 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.9264. Min Act: -0.1700
Data Index: 5640200 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.8952. Min Act: -0.1700
Data Index: 5640201 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.7702. Min Act: -0.1700
Data Index: 2105621 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.7702. Min Act: -0.1700
Data Index: 1783968 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.7077. Min Act: -0.1700
Data Index: 917677 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.7077. Min Act: -0.1700
Data Index: 905410 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.6764. Min Act: -0.1700
Data Index: 7492110 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.6764. Min Act: -0.1700
Data Index: 5189442 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.6764. Min Act: -0.1700
Data Index: 6012362 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.6764. Min Act: -0.1700
Data Index: 2065250 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.6139. Min Act: -0.1700
Data Index: 8592035 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.5827. Min Act: -0.1700
Data Index: 7083174 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.5202. Min Act: -0.1700
Data Index: 43669 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.5202. Min Act: -0.1700
Data Index: 93279 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2389. Min Range: -8.2389
Max Act: 7.5202. Min Act: -0.1700
Data Index: 757193 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #19