Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6181 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3181. Min Range: -7.3181
Max Act: 7.3181. Min Act: -0.1700
Data Index: 76839 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3181. Min Range: -7.3181
Max Act: 7.2556. Min Act: -0.1700
Data Index: 8244689 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3181. Min Range: -7.3181
Max Act: 7.0994. Min Act: -0.1700
Data Index: 6081956 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.9431. Min Act: -0.1700
Data Index: 7779001 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.9119. Min Act: -0.1700
Data Index: 1333566 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.8494. Min Act: -0.1700
Data Index: 4712990 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.8181. Min Act: -0.1700
Data Index: 4628249 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.8181. Min Act: -0.1700
Data Index: 1439037 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6931. Min Act: -0.1700
Data Index: 6495215 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.7556. Min Act: -0.1700
Data Index: 4341560 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6931. Min Act: -0.1700
Data Index: 365424 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6619. Min Act: -0.1700
Data Index: 3325312 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6619. Min Act: -0.1700
Data Index: 7111768 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6619. Min Act: -0.1700
Data Index: 3146029 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6931. Min Act: -0.1700
Data Index: 2612594 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6306. Min Act: -0.1700
Data Index: 8756440 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.6306. Min Act: -0.1700
Data Index: 8362022 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.5994. Min Act: -0.1700
Data Index: 6558312 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.5994. Min Act: -0.1700
Data Index: 8312411 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3181. Min Range: -7.3181
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7944730 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19