Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2924 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.2157. Min Act: -0.1700
Data Index: 6037553 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.2157. Min Act: -0.1700
Data Index: 7767338 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1532. Min Act: -0.1700
Data Index: 3004539 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1845. Min Act: -0.1700
Data Index: 3230735 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1845. Min Act: -0.1700
Data Index: 6778551 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1532. Min Act: -0.1700
Data Index: 7505098 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1220. Min Act: -0.1700
Data Index: 2956126 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1220. Min Act: -0.1700
Data Index: 720099 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1220. Min Act: -0.1700
Data Index: 3654024 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1532. Min Act: -0.1700
Data Index: 1638205 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1220. Min Act: -0.1700
Data Index: 1081970 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.1220. Min Act: -0.1700
Data Index: 2223514 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 8063101 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 8061030 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 3293802 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 1889670 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0595. Min Act: -0.1700
Data Index: 1797768 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1699
Data Index: 1220190 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 6117652 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2157. Min Range: -5.2157
Max Act: 5.0907. Min Act: -0.1700
Data Index: 465333 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19