Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4465 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.5024. Min Act: -0.1700
Data Index: 5753237 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4712. Min Act: -0.1700
Data Index: 7412422 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4712. Min Act: -0.1700
Data Index: 1226971 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4712. Min Act: -0.1700
Data Index: 2963586 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 3667804 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4712. Min Act: -0.1700
Data Index: 2508821 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 576888 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4086. Min Act: -0.1700
Data Index: 1511032 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 6993882 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 5980244 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 1835412 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 1742101 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 8775959 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4086. Min Act: -0.1700
Data Index: 4080354 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 8196564 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 3951723 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4086. Min Act: -0.1700
Data Index: 3622269 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4086. Min Act: -0.1700
Data Index: 4983337 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4086. Min Act: -0.1700
Data Index: 513081 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5024. Min Range: -4.5024
Max Act: 4.4399. Min Act: -0.1700
Data Index: 4354112 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19