Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4026 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.7440. Min Act: -0.1700
Data Index: 551331 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.4940. Min Act: -0.1700
Data Index: 469185 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.4940. Min Act: -0.1700
Data Index: 6406630 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.4940. Min Act: -0.1700
Data Index: 800272 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.4315. Min Act: -0.1700
Data Index: 6652549 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.2440. Min Act: -0.1700
Data Index: 4690400 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.1815. Min Act: -0.1700
Data Index: 5278601 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.1815. Min Act: -0.1700
Data Index: 1697692 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.1815. Min Act: -0.1700
Data Index: 1377773 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.1190. Min Act: -0.1700
Data Index: 6641298 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7440. Min Range: -9.7440
Max Act: 9.0565. Min Act: -0.1700
Data Index: 7653900 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9940. Min Act: -0.1700
Data Index: 4821153 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9940. Min Act: -0.1700
Data Index: 831977 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9940. Min Act: -0.1700
Data Index: 4750074 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9940. Min Act: -0.1700
Data Index: 6384987 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9940. Min Act: -0.1700
Data Index: 666955 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9315. Min Act: -0.1700
Data Index: 3425113 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9315. Min Act: -0.1700
Data Index: 3636888 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9315. Min Act: -0.1700
Data Index: 2162018 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7440. Min Range: -9.7440
Max Act: 8.9315. Min Act: -0.1700
Data Index: 6935002 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19