Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0765. Min Range: -5.0765
Max Act: 5.0765. Min Act: -0.1700
Data Index: 7346125 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0765. Min Range: -5.0765
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7283134 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0765. Min Range: -5.0765
Max Act: 5.0452. Min Act: -0.1700
Data Index: 7465515 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0765. Min Range: -5.0765
Max Act: 5.0140. Min Act: -0.1700
Data Index: 3108005 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 5250992 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 2857410 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 6716305 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 7839989 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 2074711 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9202. Min Act: -0.1700
Data Index: 2144440 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 334413 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 2440236 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 8508841 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 6586167 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9827. Min Act: -0.1700
Data Index: 2214767 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 5792063 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 5767286 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 5651949 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9515. Min Act: -0.1700
Data Index: 3397585 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0765. Min Range: -5.0765
Max Act: 4.9202. Min Act: -0.1700
Data Index: 5242437 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19