Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 392 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1536. Min Range: -6.1536
Max Act: 6.1536. Min Act: -0.1700
Data Index: 1323361 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1536. Min Range: -6.1536
Max Act: 6.1536. Min Act: -0.1700
Data Index: 1765099 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1536. Min Range: -6.1536
Max Act: 6.0911. Min Act: -0.1700
Data Index: 4966806 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1536. Min Range: -6.1536
Max Act: 6.1223. Min Act: -0.1700
Data Index: 4267259 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1536. Min Range: -6.1536
Max Act: 6.0911. Min Act: -0.1700
Data Index: 4458027 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.9661. Min Act: -0.1700
Data Index: 3257587 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8723. Min Act: -0.1700
Data Index: 4465607 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8411. Min Act: -0.1700
Data Index: 1384206 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8411. Min Act: -0.1700
Data Index: 6095920 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8723. Min Act: -0.1700
Data Index: 6095921 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8411. Min Act: -0.1700
Data Index: 2290662 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8098. Min Act: -0.1700
Data Index: 1608591 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.8098. Min Act: -0.1700
Data Index: 755301 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7786. Min Act: -0.1700
Data Index: 3867095 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7786. Min Act: -0.1700
Data Index: 6361827 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7473. Min Act: -0.1700
Data Index: 546023 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7473. Min Act: -0.1700
Data Index: 7352295 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7161. Min Act: -0.1700
Data Index: 480989 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7161. Min Act: -0.1700
Data Index: 5589831 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1536. Min Range: -6.1536
Max Act: 5.7161. Min Act: -0.1700
Data Index: 6263592 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #19