Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3804 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.3377. Min Act: -0.1700
Data Index: 8699387 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.3065. Min Act: -0.1700
Data Index: 5821862 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2752. Min Act: -0.1700
Data Index: 6988730 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2752. Min Act: -0.1700
Data Index: 341053 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2752. Min Act: -0.1700
Data Index: 6823353 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 541172 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 3196168 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 8532039 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 497640 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 5007566 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 784687 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2440. Min Act: -0.1700
Data Index: 784659 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2127. Min Act: -0.1700
Data Index: 7467731 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2127. Min Act: -0.1700
Data Index: 2361994 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2127. Min Act: -0.1700
Data Index: 341024 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.1815. Min Act: -0.1700
Data Index: 8789877 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.1502. Min Act: -0.1700
Data Index: 1631543 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.1815. Min Act: -0.1700
Data Index: 4180679 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.2127. Min Act: -0.1700
Data Index: 6883177 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3377. Min Range: -4.3377
Max Act: 4.1502. Min Act: -0.1700
Data Index: 3868751 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19