Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.7565. Min Act: -0.1700
Data Index: 3807541 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.7565. Min Act: -0.1700
Data Index: 5595633 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2940847 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.5378. Min Act: -0.1700
Data Index: 7747988 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.5378. Min Act: -0.1700
Data Index: 1053502 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.5378. Min Act: -0.1700
Data Index: 5606749 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.5065. Min Act: -0.1700
Data Index: 2883396 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.5065. Min Act: -0.1700
Data Index: 6179602 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4753. Min Act: -0.1700
Data Index: 1701726 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4753. Min Act: -0.1700
Data Index: 1533382 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4753. Min Act: -0.1700
Data Index: 3324376 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4753. Min Act: -0.1700
Data Index: 1800970 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4440. Min Act: -0.1700
Data Index: 6617153 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4128. Min Act: -0.1700
Data Index: 5820148 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4128. Min Act: -0.1700
Data Index: 8077451 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.4128. Min Act: -0.1700
Data Index: 4572262 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4938949 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3815. Min Act: -0.1700
Data Index: 1334989 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3815. Min Act: -0.1700
Data Index: 4726126 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7565. Min Range: -5.7565
Max Act: 5.3815. Min Act: -0.1700
Data Index: 3094081 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #19