Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3214 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.9634. Min Act: -0.1700
Data Index: 6630745 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.7446. Min Act: -0.1700
Data Index: 2153784 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.6821. Min Act: -0.1700
Data Index: 2455633 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.6509. Min Act: -0.1700
Data Index: 4709258 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.6509. Min Act: -0.1700
Data Index: 1543225 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.5571. Min Act: -0.1700
Data Index: 3576181 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.5571. Min Act: -0.1700
Data Index: 222414 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4946. Min Act: -0.1700
Data Index: 4951914 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4946. Min Act: -0.1700
Data Index: 5019192 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4321. Min Act: -0.1700
Data Index: 8741166 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4321. Min Act: -0.1700
Data Index: 6640194 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4009. Min Act: -0.1700
Data Index: 3276076 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4009. Min Act: -0.1700
Data Index: 3659877 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.3384. Min Act: -0.1700
Data Index: 563286 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.3696. Min Act: -0.1700
Data Index: 8592874 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.4009. Min Act: -0.1700
Data Index: 2376887 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.3071. Min Act: -0.1700
Data Index: 3657199 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.2759. Min Act: -0.1700
Data Index: 8033668 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.2759. Min Act: -0.1700
Data Index: 2321667 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9634. Min Range: -6.9634
Max Act: 6.2759. Min Act: -0.1700
Data Index: 6788204 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #19