Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1477 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2230. Min Range: -3.2230
Max Act: 3.2230. Min Act: -0.1700
Data Index: 8112734 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2230. Min Range: -3.2230
Max Act: 3.0340. Min Act: -0.1700
Data Index: 755294 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2230. Min Range: -3.2230
Max Act: 3.0182. Min Act: -0.1700
Data Index: 3591856 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.9866. Min Act: -0.1700
Data Index: 4012022 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.9708. Min Act: -0.1700
Data Index: 5424987 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.9391. Min Act: -0.1700
Data Index: 5787579 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.9391. Min Act: -0.1700
Data Index: 4390782 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8757. Min Act: -0.1700
Data Index: 2688088 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8599. Min Act: -0.1700
Data Index: 8095222 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8599. Min Act: -0.1700
Data Index: 4173441 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8599. Min Act: -0.1700
Data Index: 851377 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8440. Min Act: -0.1700
Data Index: 2370125 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8440. Min Act: -0.1700
Data Index: 4137695 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8440. Min Act: -0.1700
Data Index: 810768 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8440. Min Act: -0.1700
Data Index: 720137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8281. Min Act: -0.1700
Data Index: 3632232 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8281. Min Act: -0.1700
Data Index: 7583737 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8122. Min Act: -0.1700
Data Index: 6436655 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8281. Min Act: -0.1700
Data Index: 6157251 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2230. Min Range: -3.2230
Max Act: 2.8122. Min Act: -0.1700
Data Index: 5817583 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19