Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3181 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1515. Min Range: -6.1515
Max Act: 6.1515. Min Act: -0.1700
Data Index: 2066964 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1515. Min Range: -6.1515
Max Act: 6.0265. Min Act: -0.1700
Data Index: 5027660 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1515. Min Range: -6.1515
Max Act: 6.0265. Min Act: -0.1700
Data Index: 6389003 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9952. Min Act: -0.1700
Data Index: 7710086 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9952. Min Act: -0.1700
Data Index: 8488008 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9952. Min Act: -0.1700
Data Index: 2541507 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9952. Min Act: -0.1699
Data Index: 5401148 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1515. Min Range: -6.1515
Max Act: 6.0265. Min Act: -0.1699
Data Index: 4357075 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1700
Data Index: 162410 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1700
Data Index: 110228 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9327. Min Act: -0.1700
Data Index: 7478181 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9952. Min Act: -0.1700
Data Index: 1103622 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1699
Data Index: 3952515 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1700
Data Index: 93738 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1700
Data Index: 4877802 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9640. Min Act: -0.1700
Data Index: 5230584 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9327. Min Act: -0.1700
Data Index: 7247085 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9327. Min Act: -0.1700
Data Index: 3742362 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9327. Min Act: -0.1700
Data Index: 4856581 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1515. Min Range: -6.1515
Max Act: 5.9327. Min Act: -0.1700
Data Index: 1673039 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #19