Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5257 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.7613. Min Act: -0.1700
Data Index: 1281105 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.2300. Min Act: -0.1700
Data Index: 3951518 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.1987. Min Act: -0.1700
Data Index: 2759117 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.1675. Min Act: -0.1700
Data Index: 1159860 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.1675. Min Act: -0.1700
Data Index: 31347 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.0737. Min Act: -0.1700
Data Index: 5888480 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.0112. Min Act: -0.1700
Data Index: 2786880 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7613. Min Range: -4.7613
Max Act: 4.0112. Min Act: -0.1700
Data Index: 3086872 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9799. Min Act: -0.1700
Data Index: 7292997 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9799. Min Act: -0.1700
Data Index: 4027840 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 6893064 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 927081 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 3121648 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 338067 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 413219 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9487. Min Act: -0.1700
Data Index: 3659413 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 1997644 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 4396200 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 5230349 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7613. Min Range: -4.7613
Max Act: 3.9174. Min Act: -0.1700
Data Index: 1672577 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19