Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4081 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0247. Min Range: -6.0247
Max Act: 6.0247. Min Act: -0.1700
Data Index: 5348749 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.9622. Min Act: -0.1700
Data Index: 8775171 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.9622. Min Act: -0.1700
Data Index: 6841069 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8997. Min Act: -0.1700
Data Index: 5026705 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.9622. Min Act: -0.1700
Data Index: 5274974 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.9622. Min Act: -0.1700
Data Index: 8277623 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.9310. Min Act: -0.1700
Data Index: 3943679 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3943678 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8997. Min Act: -0.1700
Data Index: 5679737 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8997. Min Act: -0.1700
Data Index: 3943677 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8685. Min Act: -0.1700
Data Index: 5996119 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8997. Min Act: -0.1700
Data Index: 2159849 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8685. Min Act: -0.1700
Data Index: 8513858 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8372. Min Act: -0.1700
Data Index: 3580956 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8685. Min Act: -0.1700
Data Index: 7121410 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6917017 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8372. Min Act: -0.1700
Data Index: 239520 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6163794 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8060. Min Act: -0.1700
Data Index: 1386864 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0247. Min Range: -6.0247
Max Act: 5.8060. Min Act: -0.1700
Data Index: 6917016 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #19