Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1172 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.5084. Min Act: -0.1700
Data Index: 838648 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.4144. Min Act: -0.1700
Data Index: 3431709 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.2575. Min Act: -0.1700
Data Index: 6052196 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.2575. Min Act: -0.1700
Data Index: 3001995 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.2103. Min Act: -0.1700
Data Index: 6404849 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1946. Min Act: -0.1700
Data Index: 1977619 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1789. Min Act: -0.1700
Data Index: 7519140 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1946. Min Act: -0.1700
Data Index: 728906 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3638577 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1789. Min Act: -0.1700
Data Index: 3321502 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1631. Min Act: -0.1700
Data Index: 2450147 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1631. Min Act: -0.1700
Data Index: 515820 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1474. Min Act: -0.1700
Data Index: 8026275 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1631. Min Act: -0.1700
Data Index: 1126266 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1474. Min Act: -0.1700
Data Index: 6428249 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1474. Min Act: -0.1700
Data Index: 8782074 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1159. Min Act: -0.1700
Data Index: 3347298 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1159. Min Act: -0.1700
Data Index: 6777565 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1159. Min Act: -0.1700
Data Index: 1791097 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5084. Min Range: -3.5084
Max Act: 3.1001. Min Act: -0.1700
Data Index: 4175941 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19