Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2136 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.5633. Min Act: -0.1699
Data Index: 8082781 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.5195. Min Act: -0.1700
Data Index: 2872227 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4844. Min Act: -0.1700
Data Index: 1335203 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4756. Min Act: -0.1699
Data Index: 6504084 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4756. Min Act: -0.1700
Data Index: 3407143 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4404. Min Act: -0.1646
Data Index: 8575794 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4492. Min Act: -0.1700
Data Index: 52124 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4316. Min Act: -0.1699
Data Index: 1243113 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4404. Min Act: -0.1676
Data Index: 236493 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4316. Min Act: -0.1697
Data Index: 5376115 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4228. Min Act: -0.1684
Data Index: 5900684 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4228. Min Act: -0.1700
Data Index: 6455236 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4228. Min Act: -0.1700
Data Index: 814591 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4140. Min Act: -0.1700
Data Index: 8771599 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4052. Min Act: -0.1696
Data Index: 5862841 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.3964. Min Act: -0.1687
Data Index: 836658 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4052. Min Act: -0.1693
Data Index: 2197548 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4052. Min Act: -0.1700
Data Index: 6066401 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.4052. Min Act: -0.1700
Data Index: 4933423 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5633. Min Range: -1.5633
Max Act: 1.3964. Min Act: -0.1700
Data Index: 6731835 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19