Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2552 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.3450. Min Range: -7.3450
Max Act: 7.3450. Min Act: -0.1700
Data Index: 2185241 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.7513. Min Act: -0.1700
Data Index: 2844995 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.7200. Min Act: -0.1700
Data Index: 3736041 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.5950. Min Act: -0.1700
Data Index: 6466615 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.5950. Min Act: -0.1700
Data Index: 2561275 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.5013. Min Act: -0.1700
Data Index: 3306568 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.5013. Min Act: -0.1700
Data Index: 1775032 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.5013. Min Act: -0.1700
Data Index: 5947771 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.4700. Min Act: -0.1700
Data Index: 773657 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.4388. Min Act: -0.1700
Data Index: 8468824 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 6006195 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.4075. Min Act: -0.1700
Data Index: 8095053 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3763. Min Act: -0.1700
Data Index: 4769834 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3763. Min Act: -0.1700
Data Index: 7010279 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3763. Min Act: -0.1700
Data Index: 3505112 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 2163952 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 3244639 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 7053951 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 1620772 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3450. Min Range: -7.3450
Max Act: 6.3450. Min Act: -0.1700
Data Index: 4769833 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #19