Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4714 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.6949. Min Act: -0.1700
Data Index: 567675 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.5074. Min Act: -0.1700
Data Index: 6916609 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.4761. Min Act: -0.1700
Data Index: 6682192 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 2555258 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.4449. Min Act: -0.1700
Data Index: 3523217 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3824. Min Act: -0.1700
Data Index: 1456318 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3824. Min Act: -0.1700
Data Index: 2109142 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.3824. Min Act: -0.1700
Data Index: 6628295 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1949. Min Act: -0.1700
Data Index: 8408140 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1636. Min Act: -0.1700
Data Index: 1599743 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1949. Min Act: -0.1700
Data Index: 4751812 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1011. Min Act: -0.1700
Data Index: 160110 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1011. Min Act: -0.1700
Data Index: 6175534 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.1011. Min Act: -0.1700
Data Index: 478628 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5573859 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 5599922 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6949. Min Range: -6.6949
Max Act: 5.9761. Min Act: -0.1700
Data Index: 6023693 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 147728 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.0386. Min Act: -0.1700
Data Index: 5440209 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6949. Min Range: -6.6949
Max Act: 6.0074. Min Act: -0.1700
Data Index: 8441157 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19