Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3930 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.6946. Min Act: -0.1700
Data Index: 3042734 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.6786. Min Act: -0.1700
Data Index: 4571996 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.6143. Min Act: -0.1700
Data Index: 3257602 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.6304. Min Act: -0.1700
Data Index: 5932240 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5983. Min Act: -0.1700
Data Index: 8016653 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5660. Min Act: -0.1700
Data Index: 507542 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5660. Min Act: -0.1700
Data Index: 1913008 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5499. Min Act: -0.1700
Data Index: 4790902 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5499. Min Act: -0.1700
Data Index: 7095523 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5337. Min Act: -0.1700
Data Index: 970257 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5499. Min Act: -0.1700
Data Index: 1087876 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5176. Min Act: -0.1700
Data Index: 5002977 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5014. Min Act: -0.1700
Data Index: 6560846 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5176. Min Act: -0.1700
Data Index: 6456998 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.4852. Min Act: -0.1700
Data Index: 7902392 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5176. Min Act: -0.1700
Data Index: 6045397 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.5014. Min Act: -0.1700
Data Index: 5557386 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.4852. Min Act: -0.1700
Data Index: 2143022 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.4852. Min Act: -0.1700
Data Index: 3425004 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6946. Min Range: -2.6946
Max Act: 2.4689. Min Act: -0.1700
Data Index: 2853469 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19