Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5191 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6735. Min Act: -0.1700
Data Index: 3875400 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6735. Min Act: -0.1700
Data Index: 3280164 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6735. Min Act: -0.1700
Data Index: 2184809 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6110. Min Act: -0.1700
Data Index: 5342174 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6110. Min Act: -0.1700
Data Index: 260085 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.5485. Min Act: -0.1700
Data Index: 7471102 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.5485. Min Act: -0.1700
Data Index: 4389054 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.6110. Min Act: -0.1700
Data Index: 782040 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.5485. Min Act: -0.1700
Data Index: 3280163 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4860. Min Act: -0.1700
Data Index: 7248136 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.5485. Min Act: -0.1700
Data Index: 624005 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.5485. Min Act: -0.1700
Data Index: 4120409 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4548. Min Act: -0.1700
Data Index: 3130749 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4860. Min Act: -0.1700
Data Index: 1768742 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4860. Min Act: -0.1700
Data Index: 5933909 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4860. Min Act: -0.1700
Data Index: 4628090 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4548. Min Act: -0.1700
Data Index: 8132608 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4548. Min Act: -0.1700
Data Index: 5627095 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4235. Min Act: -0.1700
Data Index: 7478041 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6735. Min Range: -7.6735
Max Act: 7.4548. Min Act: -0.1700
Data Index: 5460267 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #19