Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3870 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.9294. Min Act: -0.1700
Data Index: 3101239 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.6169. Min Act: -0.1700
Data Index: 5161935 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.4919. Min Act: -0.1700
Data Index: 187347 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.4919. Min Act: -0.1700
Data Index: 410413 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.4294. Min Act: -0.1700
Data Index: 6735855 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.3669. Min Act: -0.1700
Data Index: 6033936 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.3044. Min Act: -0.1700
Data Index: 3494252 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.3044. Min Act: -0.1700
Data Index: 7774681 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.3044. Min Act: -0.1700
Data Index: 7035272 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.2419. Min Act: -0.1700
Data Index: 8532011 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1794. Min Act: -0.1700
Data Index: 508303 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1794. Min Act: -0.1700
Data Index: 167337 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1169. Min Act: -0.1700
Data Index: 4939821 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1169. Min Act: -0.1700
Data Index: 5735250 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1169. Min Act: -0.1700
Data Index: 162841 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.1169. Min Act: -0.1700
Data Index: 3527127 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.0544. Min Act: -0.1700
Data Index: 1001646 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.0544. Min Act: -0.1700
Data Index: 883693 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.0544. Min Act: -0.1700
Data Index: 6976091 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.9294. Min Range: -10.9294
Max Act: 10.0544. Min Act: -0.1700
Data Index: 2608704 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19