Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2123 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.8030. Min Act: -0.1700
Data Index: 3223349 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.4280. Min Act: -0.1700
Data Index: 332595 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.3967. Min Act: -0.1700
Data Index: 2128192 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.3655. Min Act: -0.1700
Data Index: 5893640 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.3342. Min Act: -0.1700
Data Index: 4281114 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.3030. Min Act: -0.1700
Data Index: 7186922 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.2717. Min Act: -0.1700
Data Index: 5270862 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.2092. Min Act: -0.1700
Data Index: 6506164 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.2092. Min Act: -0.1700
Data Index: 7398966 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1780. Min Act: -0.1700
Data Index: 3926075 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1780. Min Act: -0.1700
Data Index: 553238 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1780. Min Act: -0.1700
Data Index: 5675037 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1467. Min Act: -0.1700
Data Index: 2225953 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1155. Min Act: -0.1700
Data Index: 139637 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1467. Min Act: -0.1700
Data Index: 7531261 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1780. Min Act: -0.1700
Data Index: 1573574 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1155. Min Act: -0.1700
Data Index: 7263056 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.1155. Min Act: -0.1700
Data Index: 6770433 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.0842. Min Act: -0.1700
Data Index: 7147713 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8030. Min Range: -5.8030
Max Act: 5.0842. Min Act: -0.1700
Data Index: 809972 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19