Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 593 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.2576. Min Act: -0.1700
Data Index: 8691736 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.2889. Min Act: -0.1700
Data Index: 7942255 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.2889. Min Act: -0.1700
Data Index: 5856731 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.2576. Min Act: -0.1700
Data Index: 5254421 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.2264. Min Act: -0.1700
Data Index: 116909 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.0701. Min Act: -0.1700
Data Index: 5545359 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.0389. Min Act: -0.1700
Data Index: 2943441 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2889. Min Range: -7.2889
Max Act: 7.0701. Min Act: -0.1700
Data Index: 8812502 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.9451. Min Act: -0.1700
Data Index: 1840481 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.9139. Min Act: -0.1700
Data Index: 4347003 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8826. Min Act: -0.1700
Data Index: 6445119 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.9139. Min Act: -0.1700
Data Index: 8390922 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.9451. Min Act: -0.1700
Data Index: 428980 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.9451. Min Act: -0.1700
Data Index: 7626926 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8514. Min Act: -0.1700
Data Index: 6549816 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8826. Min Act: -0.1700
Data Index: 6687936 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8514. Min Act: -0.1700
Data Index: 4646428 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8201. Min Act: -0.1700
Data Index: 1660623 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8514. Min Act: -0.1700
Data Index: 8149403 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2889. Min Range: -7.2889
Max Act: 6.8201. Min Act: -0.1700
Data Index: 5700937 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19