Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6244 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0946. Min Range: -6.0946
Max Act: 6.0946. Min Act: -0.1700
Data Index: 1686707 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.9384. Min Act: -0.1700
Data Index: 8536461 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.9071. Min Act: -0.1700
Data Index: 1686706 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.8759. Min Act: -0.1700
Data Index: 3621313 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.7196. Min Act: -0.1700
Data Index: 1829927 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.6884. Min Act: -0.1700
Data Index: 3563348 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.6259. Min Act: -0.1700
Data Index: 4363162 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.4384. Min Act: -0.1700
Data Index: 2928724 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 8419361 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.4071. Min Act: -0.1700
Data Index: 1353427 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3164827 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.3134. Min Act: -0.1700
Data Index: 260429 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.2821. Min Act: -0.1700
Data Index: 7476183 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.3134. Min Act: -0.1700
Data Index: 1269320 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.2821. Min Act: -0.1700
Data Index: 4100844 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.2509. Min Act: -0.1700
Data Index: 1314292 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.2196. Min Act: -0.1700
Data Index: 3394969 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.1884. Min Act: -0.1700
Data Index: 7520952 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.1884. Min Act: -0.1700
Data Index: 5492711 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0946. Min Range: -6.0946
Max Act: 5.1571. Min Act: -0.1700
Data Index: 6238390 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19