Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1418 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2392. Min Range: -9.2392
Max Act: 9.2392. Min Act: -0.1700
Data Index: 1307213 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2392. Min Range: -9.2392
Max Act: 9.2392. Min Act: -0.1700
Data Index: 3876864 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.9892. Min Act: -0.1700
Data Index: 5438427 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.9892. Min Act: -0.1700
Data Index: 6551189 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.8642. Min Act: -0.1700
Data Index: 5342908 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.8017. Min Act: -0.1700
Data Index: 8337127 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.8017. Min Act: -0.1700
Data Index: 789937 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.8642. Min Act: -0.1700
Data Index: 7550417 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.7392. Min Act: -0.1700
Data Index: 4051874 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.7392. Min Act: -0.1700
Data Index: 1128873 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.6142. Min Act: -0.1700
Data Index: 4927847 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.6142. Min Act: -0.1700
Data Index: 1256717 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.6142. Min Act: -0.1700
Data Index: 846038 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.4892. Min Act: -0.1700
Data Index: 8115380 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.5517. Min Act: -0.1700
Data Index: 2946542 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.5517. Min Act: -0.1700
Data Index: 547363 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.4892. Min Act: -0.1700
Data Index: 5715785 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.4892. Min Act: -0.1700
Data Index: 3202943 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.4892. Min Act: -0.1700
Data Index: 1307946 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2392. Min Range: -9.2392
Max Act: 8.5517. Min Act: -0.1700
Data Index: 922024 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19