Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1789 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.6293. Min Act: -0.1700
Data Index: 3676730 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5197. Min Act: -0.1700
Data Index: 4813430 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5510. Min Act: -0.1700
Data Index: 3600072 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5353. Min Act: -0.1700
Data Index: 528177 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5353. Min Act: -0.1700
Data Index: 1377026 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5197. Min Act: -0.1700
Data Index: 5155439 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5040. Min Act: -0.1700
Data Index: 8427781 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5040. Min Act: -0.1700
Data Index: 2078079 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.5040. Min Act: -0.1700
Data Index: 6781900 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4727. Min Act: -0.1700
Data Index: 500638 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4884. Min Act: -0.1700
Data Index: 3377817 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4884. Min Act: -0.1700
Data Index: 3203762 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4727. Min Act: -0.1700
Data Index: 601724 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4570. Min Act: -0.1700
Data Index: 1813462 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4570. Min Act: -0.1700
Data Index: 359834 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4727. Min Act: -0.1700
Data Index: 1813458 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4727. Min Act: -0.1700
Data Index: 828682 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4570. Min Act: -0.1700
Data Index: 2599826 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4414. Min Act: -0.1700
Data Index: 5785795 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6293. Min Range: -3.6293
Max Act: 3.4570. Min Act: -0.1700
Data Index: 5794196 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19