Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1195 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.3293. Min Act: -0.1700
Data Index: 3088898 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2800. Min Act: -0.1700
Data Index: 6905176 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2470. Min Act: -0.1700
Data Index: 1160037 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2470. Min Act: -0.1700
Data Index: 5378395 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2470. Min Act: -0.1700
Data Index: 3584062 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2139. Min Act: -0.1700
Data Index: 8685652 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.2139. Min Act: -0.1700
Data Index: 5198130 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1640. Min Act: -0.1700
Data Index: 2461733 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1807. Min Act: -0.1700
Data Index: 7562212 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1807. Min Act: -0.1700
Data Index: 5735656 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1807. Min Act: -0.1700
Data Index: 7111500 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1640. Min Act: -0.1700
Data Index: 1644924 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1474. Min Act: -0.1700
Data Index: 841083 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1474. Min Act: -0.1700
Data Index: 5668277 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1474. Min Act: -0.1700
Data Index: 2421738 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1140. Min Act: -0.1700
Data Index: 5472766 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1140. Min Act: -0.1700
Data Index: 3155864 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1474. Min Act: -0.1700
Data Index: 5690913 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1140. Min Act: -0.1700
Data Index: 2925478 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3293. Min Range: -2.3293
Max Act: 2.1307. Min Act: -0.1700
Data Index: 4720746 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #19