Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.7446. Min Act: -0.1700
Data Index: 2550152 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.7134. Min Act: -0.1700
Data Index: 8060670 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.7134. Min Act: -0.1700
Data Index: 149920 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.6821. Min Act: -0.1700
Data Index: 2041260 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5884. Min Act: -0.1700
Data Index: 7603177 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5884. Min Act: -0.1700
Data Index: 2982215 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5571. Min Act: -0.1700
Data Index: 3069571 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5571. Min Act: -0.1700
Data Index: 6512277 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5259. Min Act: -0.1700
Data Index: 2118295 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5259. Min Act: -0.1700
Data Index: 5250376 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.5259. Min Act: -0.1700
Data Index: 3452304 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 7354552 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 6917313 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4387887 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4946. Min Act: -0.1700
Data Index: 6568205 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 7754935 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 2047042 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 7234183 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4634. Min Act: -0.1700
Data Index: 4407200 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7446. Min Range: -6.7446
Max Act: 6.4321. Min Act: -0.1700
Data Index: 2510696 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19