Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3886 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.8168. Min Act: -0.1700
Data Index: 4633296 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.7856. Min Act: -0.1700
Data Index: 3486548 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.7231. Min Act: -0.1700
Data Index: 8029462 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.6606. Min Act: -0.1700
Data Index: 293707 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6107967 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.6293. Min Act: -0.1700
Data Index: 110467 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5981. Min Act: -0.1700
Data Index: 4141101 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.6293. Min Act: -0.1700
Data Index: 6030056 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5981. Min Act: -0.1700
Data Index: 1183407 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5356. Min Act: -0.1700
Data Index: 7749522 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5668. Min Act: -0.1700
Data Index: 1780970 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5528532 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5356. Min Act: -0.1700
Data Index: 5708886 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.5043. Min Act: -0.1700
Data Index: 6057560 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4731. Min Act: -0.1700
Data Index: 4183248 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4731. Min Act: -0.1700
Data Index: 4217748 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4731. Min Act: -0.1700
Data Index: 1524737 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4418. Min Act: -0.1700
Data Index: 3670842 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4731. Min Act: -0.1700
Data Index: 3190491 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8168. Min Range: -5.8168
Max Act: 5.4418. Min Act: -0.1700
Data Index: 3071076 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19