Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2615 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.8868. Min Act: -0.1700
Data Index: 4934665 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.6053. Min Act: -0.1700
Data Index: 3114964 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.5583. Min Act: -0.1700
Data Index: 8594212 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.5270. Min Act: -0.1700
Data Index: 2813929 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4957. Min Act: -0.1700
Data Index: 680235 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4957. Min Act: -0.1700
Data Index: 6095013 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4800. Min Act: -0.1700
Data Index: 3000846 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4957. Min Act: -0.1700
Data Index: 8271709 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4800. Min Act: -0.1700
Data Index: 2519684 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4800. Min Act: -0.1700
Data Index: 6674605 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4330. Min Act: -0.1700
Data Index: 4887465 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4487. Min Act: -0.1700
Data Index: 4767539 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4330. Min Act: -0.1700
Data Index: 3239037 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4330. Min Act: -0.1700
Data Index: 6011774 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.3860. Min Act: -0.1700
Data Index: 6717388 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4174. Min Act: -0.1700
Data Index: 3695793 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4174. Min Act: -0.1700
Data Index: 2489618 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.3860. Min Act: -0.1700
Data Index: 6762130 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.4017. Min Act: -0.1700
Data Index: 3339497 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8868. Min Range: -3.8868
Max Act: 3.3703. Min Act: -0.1700
Data Index: 160195 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19