Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2169 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0903. Min Range: -3.0903
Max Act: 3.0903. Min Act: -0.1700
Data Index: 4362312 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.9956. Min Act: -0.1700
Data Index: 8685471 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.9323. Min Act: -0.1700
Data Index: 5910910 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.9323. Min Act: -0.1700
Data Index: 7817951 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8689. Min Act: -0.1700
Data Index: 3130232 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8847. Min Act: -0.1700
Data Index: 6652568 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8689. Min Act: -0.1700
Data Index: 338638 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8212. Min Act: -0.1700
Data Index: 4299895 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8371. Min Act: -0.1700
Data Index: 1330514 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8053. Min Act: -0.1700
Data Index: 8635950 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7894. Min Act: -0.1700
Data Index: 688156 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.8212. Min Act: -0.1700
Data Index: 8685474 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7894. Min Act: -0.1700
Data Index: 1988658 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7894. Min Act: -0.1700
Data Index: 1960805 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7575. Min Act: -0.1700
Data Index: 7332421 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7894. Min Act: -0.1700
Data Index: 137021 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7255. Min Act: -0.1700
Data Index: 6885403 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7415. Min Act: -0.1700
Data Index: 4470495 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7095. Min Act: -0.1700
Data Index: 4646986 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0903. Min Range: -3.0903
Max Act: 2.7255. Min Act: -0.1700
Data Index: 4946590 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #19