Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2496 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0240. Min Range: -3.0240
Max Act: 3.0240. Min Act: -0.1700
Data Index: 1800370 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7702. Min Act: -0.1700
Data Index: 261302 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7223. Min Act: -0.1700
Data Index: 1621857 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7383. Min Act: -0.1700
Data Index: 5700975 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7383. Min Act: -0.1700
Data Index: 1567409 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7223. Min Act: -0.1700
Data Index: 4089513 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7383. Min Act: -0.1700
Data Index: 5481424 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.7063. Min Act: -0.1700
Data Index: 1254329 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 1610066 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6903. Min Act: -0.1700
Data Index: 6695963 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6903. Min Act: -0.1700
Data Index: 935252 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 5055786 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 2222893 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6903. Min Act: -0.1700
Data Index: 6155600 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 7288127 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 28775 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6903. Min Act: -0.1700
Data Index: 629972 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6583. Min Act: -0.1700
Data Index: 4971346 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6743. Min Act: -0.1700
Data Index: 3282608 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0240. Min Range: -3.0240
Max Act: 2.6422. Min Act: -0.1700
Data Index: 1588103 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #19