Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1536 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.4640. Min Act: -0.1700
Data Index: 6498255 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.4314. Min Act: -0.1700
Data Index: 430483 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3661. Min Act: -0.1700
Data Index: 4202051 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3334. Min Act: -0.1700
Data Index: 7093417 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3661. Min Act: -0.1700
Data Index: 2260320 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3170. Min Act: -0.1700
Data Index: 7090540 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3170. Min Act: -0.1700
Data Index: 1330291 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3170. Min Act: -0.1700
Data Index: 8774409 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3334. Min Act: -0.1700
Data Index: 182693 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.3170. Min Act: -0.1700
Data Index: 6084032 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2841. Min Act: -0.1700
Data Index: 983367 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2676. Min Act: -0.1700
Data Index: 7397967 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 995406 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2676. Min Act: -0.1700
Data Index: 6445078 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2676. Min Act: -0.1700
Data Index: 3311248 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 4887221 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 6071009 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 3823406 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 7118148 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4640. Min Range: -2.4640
Max Act: 2.2511. Min Act: -0.1700
Data Index: 1062534 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #19