Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3071 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.2154. Min Range: -11.2154
Max Act: 11.2154. Min Act: -0.1700
Data Index: 1033682 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.9654. Min Act: -0.1700
Data Index: 2652614 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.5904. Min Act: -0.1700
Data Index: 6828062 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.5279. Min Act: -0.1700
Data Index: 97101 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.4654. Min Act: -0.1700
Data Index: 7118980 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.4654. Min Act: -0.1700
Data Index: 1293344 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.4029. Min Act: -0.1700
Data Index: 3002944 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.4029. Min Act: -0.1700
Data Index: 7684245 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.4029. Min Act: -0.1700
Data Index: 8615563 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 5270219 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.3404. Min Act: -0.1700
Data Index: 4340977 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.3404. Min Act: -0.1700
Data Index: 4146616 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 6753595 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.3404. Min Act: -0.1700
Data Index: 122443 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 996792 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 2727630 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 1331054 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2154. Min Act: -0.1700
Data Index: 6986291 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2154. Min Act: -0.1700
Data Index: 4921059 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.2154. Min Range: -11.2154
Max Act: 10.2779. Min Act: -0.1700
Data Index: 1295274 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19