Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3701 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.4143. Min Act: -0.1700
Data Index: 3245673 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.3830. Min Act: -0.1700
Data Index: 4784165 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.3518. Min Act: -0.1700
Data Index: 7304643 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.3205. Min Act: -0.1700
Data Index: 4666443 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.3205. Min Act: -0.1700
Data Index: 3264761 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 3779030 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 6255961 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 8589582 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2268. Min Act: -0.1700
Data Index: 3565614 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 4307524 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 1930633 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 1756399 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 5848654 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2893. Min Act: -0.1700
Data Index: 6728548 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 5318111 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 6563586 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 7332892 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 6147297 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2580. Min Act: -0.1700
Data Index: 3822733 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4143. Min Range: -4.4143
Max Act: 4.2268. Min Act: -0.1700
Data Index: 1472485 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #19