Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.8689. Min Act: -0.1700
Data Index: 7578870 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.9002. Min Act: -0.1700
Data Index: 1306217 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.8377. Min Act: -0.1700
Data Index: 6572980 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.7127. Min Act: -0.1700
Data Index: 873100 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.4939. Min Act: -0.1700
Data Index: 4660206 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.4314. Min Act: -0.1700
Data Index: 6943245 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.4314. Min Act: -0.1700
Data Index: 5637974 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.4002. Min Act: -0.1700
Data Index: 6151737 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 1142580 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.3377. Min Act: -0.1700
Data Index: 376634 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.3064. Min Act: -0.1700
Data Index: 3060100 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.3064. Min Act: -0.1700
Data Index: 102228 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 3352277 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2439. Min Act: -0.1700
Data Index: 8484152 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 8635943 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2752. Min Act: -0.1700
Data Index: 3584437 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2439. Min Act: -0.1700
Data Index: 4499726 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2439. Min Act: -0.1700
Data Index: 2674565 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2439. Min Act: -0.1700
Data Index: 6774708 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9002. Min Range: -5.9002
Max Act: 5.2127. Min Act: -0.1700
Data Index: 5047570 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19