Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3965 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.6745. Min Act: -0.1700
Data Index: 2682485 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 3115690 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.7058. Min Act: -0.1700
Data Index: 5462576 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.6433. Min Act: -0.1700
Data Index: 8235988 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.5183. Min Act: -0.1700
Data Index: 3948806 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.5495. Min Act: -0.1700
Data Index: 3380405 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.4870. Min Act: -0.1700
Data Index: 7326300 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.4558. Min Act: -0.1700
Data Index: 5785623 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.4558. Min Act: -0.1700
Data Index: 1022193 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.3933. Min Act: -0.1700
Data Index: 3031730 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.4245. Min Act: -0.1700
Data Index: 2513661 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.3933. Min Act: -0.1700
Data Index: 831551 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.3620. Min Act: -0.1700
Data Index: 8392421 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2370. Min Act: -0.1700
Data Index: 7805500 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2370. Min Act: -0.1700
Data Index: 2077140 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2370. Min Act: -0.1700
Data Index: 4795480 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2995. Min Act: -0.1700
Data Index: 8489538 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2683. Min Act: -0.1700
Data Index: 6306873 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2683. Min Act: -0.1700
Data Index: 2580401 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7058. Min Range: -7.7058
Max Act: 7.2058. Min Act: -0.1700
Data Index: 4228090 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #19