Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5071 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.6144. Min Act: -0.1700
Data Index: 7425003 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.4735. Min Act: -0.1700
Data Index: 7591332 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.4735. Min Act: -0.1700
Data Index: 533125 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.4422. Min Act: -0.1700
Data Index: 2660818 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.3952. Min Act: -0.1700
Data Index: 5002279 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.3324. Min Act: -0.1700
Data Index: 3096648 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.3324. Min Act: -0.1700
Data Index: 8013259 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.3010. Min Act: -0.1700
Data Index: 5669750 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2853. Min Act: -0.1700
Data Index: 2158556 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.3010. Min Act: -0.1700
Data Index: 4997748 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2696. Min Act: -0.1700
Data Index: 44527 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2696. Min Act: -0.1700
Data Index: 6076150 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2696. Min Act: -0.1700
Data Index: 2552415 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2382. Min Act: -0.1700
Data Index: 387679 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2539. Min Act: -0.1700
Data Index: 7808001 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2382. Min Act: -0.1700
Data Index: 3670421 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2225. Min Act: -0.1700
Data Index: 6892405 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2382. Min Act: -0.1700
Data Index: 15764 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2539. Min Act: -0.1700
Data Index: 6048937 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6144. Min Range: -3.6144
Max Act: 3.2539. Min Act: -0.1700
Data Index: 2778465 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19