Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1709 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.3427. Min Act: -0.1700
Data Index: 2638295 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1384. Min Act: -0.1700
Data Index: 2269243 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1699. Min Act: -0.1700
Data Index: 4778139 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1699. Min Act: -0.1700
Data Index: 8137892 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1384. Min Act: -0.1700
Data Index: 4266862 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1384. Min Act: -0.1700
Data Index: 2246329 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1384. Min Act: -0.1700
Data Index: 539403 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1384. Min Act: -0.1700
Data Index: 232214 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1227. Min Act: -0.1700
Data Index: 1809244 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.1227. Min Act: -0.1700
Data Index: 6139475 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0912. Min Act: -0.1700
Data Index: 8115469 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0754. Min Act: -0.1700
Data Index: 4261319 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0912. Min Act: -0.1700
Data Index: 4855518 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0438. Min Act: -0.1700
Data Index: 5378902 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0754. Min Act: -0.1700
Data Index: 5961902 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0754. Min Act: -0.1700
Data Index: 7926342 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0754. Min Act: -0.1700
Data Index: 4129464 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0596. Min Act: -0.1700
Data Index: 6412346 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0596. Min Act: -0.1700
Data Index: 6738801 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3427. Min Range: -3.3427
Max Act: 3.0596. Min Act: -0.1700
Data Index: 678070 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #19