Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 156 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.6946. Min Act: -0.1700
Data Index: 7880602 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.6164. Min Act: -0.1700
Data Index: 222583 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.5694. Min Act: -0.1700
Data Index: 7234079 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.5381. Min Act: -0.1700
Data Index: 3169310 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.5224. Min Act: -0.1700
Data Index: 2661847 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4911. Min Act: -0.1700
Data Index: 8810285 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4598. Min Act: -0.1700
Data Index: 4897620 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4441. Min Act: -0.1700
Data Index: 7408743 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4598. Min Act: -0.1700
Data Index: 8825238 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4754. Min Act: -0.1700
Data Index: 6250495 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4441. Min Act: -0.1700
Data Index: 4548942 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4441. Min Act: -0.1700
Data Index: 8582328 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4284. Min Act: -0.1700
Data Index: 255312 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4284. Min Act: -0.1700
Data Index: 5172653 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4284. Min Act: -0.1700
Data Index: 4897622 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4284. Min Act: -0.1700
Data Index: 1771922 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.3971. Min Act: -0.1700
Data Index: 8391209 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.4128. Min Act: -0.1700
Data Index: 1511824 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.3971. Min Act: -0.1700
Data Index: 749797 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6946. Min Range: -3.6946
Max Act: 3.3814. Min Act: -0.1700
Data Index: 6003229 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19