Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1810 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0450. Min Act: -0.1700
Data Index: 5039312 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0450. Min Act: -0.1700
Data Index: 6266068 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0282. Min Act: -0.1700
Data Index: 1679700 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0450. Min Act: -0.1700
Data Index: 4476683 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0113. Min Act: -0.1700
Data Index: 4347919 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 4672671 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0113. Min Act: -0.1700
Data Index: 4100384 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0450. Min Range: -2.0450
Max Act: 2.0113. Min Act: -0.1700
Data Index: 1519503 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 6335058 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 4472588 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 880667 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 967126 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9944. Min Act: -0.1700
Data Index: 3686218 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 2650875 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 4895132 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 1602169 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 1687619 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 5918229 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 6205512 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0450. Min Range: -2.0450
Max Act: 1.9775. Min Act: -0.1700
Data Index: 650515 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19