Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.8989. Min Act: -0.1700
Data Index: 3976053 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.8364. Min Act: -0.1700
Data Index: 1379266 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.6489. Min Act: -0.1700
Data Index: 8803042 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.7114. Min Act: -0.1700
Data Index: 614790 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.7114. Min Act: -0.1700
Data Index: 5032707 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.6489. Min Act: -0.1700
Data Index: 8389299 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 6820916 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 746906 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 6067250 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 7237868 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 7278588 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 1393977 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 7439607 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5864. Min Act: -0.1700
Data Index: 3472092 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.4614. Min Act: -0.1700
Data Index: 4558564 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.3989. Min Act: -0.1700
Data Index: 3814000 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.4614. Min Act: -0.1700
Data Index: 1674089 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.4614. Min Act: -0.1700
Data Index: 1432862 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.4614. Min Act: -0.1700
Data Index: 8406717 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8989. Min Range: -8.8989
Max Act: 8.5239. Min Act: -0.1700
Data Index: 1851478 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19