Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3811 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.6965. Min Act: -0.1700
Data Index: 4269470 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.6965. Min Act: -0.1700
Data Index: 6306430 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.4777. Min Act: -0.1700
Data Index: 5301171 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.4777. Min Act: -0.1700
Data Index: 4919513 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.3840. Min Act: -0.1700
Data Index: 8807740 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.3527. Min Act: -0.1700
Data Index: 2420655 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 2814713 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 7619407 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.3215. Min Act: -0.1700
Data Index: 5055432 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.2277. Min Act: -0.1700
Data Index: 1213403 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.2277. Min Act: -0.1700
Data Index: 3152093 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.2277. Min Act: -0.1700
Data Index: 7861860 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1965. Min Act: -0.1700
Data Index: 5520856 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1965. Min Act: -0.1700
Data Index: 5301170 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1652. Min Act: -0.1700
Data Index: 3053634 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1652. Min Act: -0.1700
Data Index: 5301181 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1340. Min Act: -0.1700
Data Index: 7773602 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1340. Min Act: -0.1700
Data Index: 7521321 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1652. Min Act: -0.1700
Data Index: 4190638 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6965. Min Range: -7.6965
Max Act: 7.1340. Min Act: -0.1700
Data Index: 564884 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19