Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1227 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0273. Min Range: -4.0273
Max Act: 4.0273. Min Act: -0.1700
Data Index: 4109428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9960. Min Act: -0.1700
Data Index: 1306547 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9960. Min Act: -0.1700
Data Index: 5917686 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9647. Min Act: -0.1700
Data Index: 3196047 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 7488718 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 5215671 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 8030474 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 3203785 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 5640057 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9335. Min Act: -0.1700
Data Index: 900760 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 3681707 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 5979513 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 1120859 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 145787 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 3615533 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.8709. Min Act: -0.1700
Data Index: 8140081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 3441567 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.9022. Min Act: -0.1700
Data Index: 1369315 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.8709. Min Act: -0.1700
Data Index: 5342820 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0273. Min Range: -4.0273
Max Act: 3.8709. Min Act: -0.1700
Data Index: 2779586 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19