Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2139 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7750. Min Act: -0.1700
Data Index: 4035222 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7750. Min Act: -0.1700
Data Index: 1367526 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7664. Min Act: -0.1700
Data Index: 450824 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7577. Min Act: -0.1700
Data Index: 2136372 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7577. Min Act: -0.1700
Data Index: 5578568 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7491. Min Act: -0.1700
Data Index: 8299746 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7318. Min Act: -0.1700
Data Index: 623181 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7318. Min Act: -0.1700
Data Index: 5945287 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7231. Min Act: -0.1700
Data Index: 8370081 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7231. Min Act: -0.1700
Data Index: 4469125 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7231. Min Act: -0.1700
Data Index: 2140440 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7058. Min Act: -0.1700
Data Index: 5323680 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7145. Min Act: -0.1700
Data Index: 3015488 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7145. Min Act: -0.1700
Data Index: 7763898 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7058. Min Act: -0.1700
Data Index: 6514082 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7231. Min Act: -0.1700
Data Index: 4264588 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7145. Min Act: -0.1700
Data Index: 5401264 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.6885. Min Act: -0.1700
Data Index: 1930815 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.7058. Min Act: -0.1700
Data Index: 4435055 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7750. Min Range: -1.7750
Max Act: 1.6885. Min Act: -0.1700
Data Index: 1308465 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #19