Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2931 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.4998. Min Act: -0.1700
Data Index: 3415636 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.5311. Min Act: -0.1700
Data Index: 6472839 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.4998. Min Act: -0.1700
Data Index: 4320352 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.4373. Min Act: -0.1700
Data Index: 5937678 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3748. Min Act: -0.1700
Data Index: 2948614 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3748. Min Act: -0.1700
Data Index: 1343461 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3748. Min Act: -0.1700
Data Index: 2479433 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3435. Min Act: -0.1700
Data Index: 2195267 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3123. Min Act: -0.1700
Data Index: 8221514 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3123. Min Act: -0.1700
Data Index: 4147889 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3123. Min Act: -0.1700
Data Index: 7996109 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.3123. Min Act: -0.1700
Data Index: 5148354 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1593959 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2810. Min Act: -0.1700
Data Index: 4221622 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2810. Min Act: -0.1700
Data Index: 1436459 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2185. Min Act: -0.1700
Data Index: 8821598 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2498. Min Act: -0.1700
Data Index: 4158839 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2498. Min Act: -0.1700
Data Index: 8517094 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2810. Min Act: -0.1700
Data Index: 2185910 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5311. Min Range: -4.5311
Max Act: 4.2498. Min Act: -0.1700
Data Index: 196346 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #19