Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.4396. Min Act: -0.1700
Data Index: 7273168 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.4308. Min Act: -0.1674
Data Index: 7323310 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.4220. Min Act: -0.1700
Data Index: 2487268 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.4044. Min Act: -0.1694
Data Index: 7237720 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.4044. Min Act: -0.1699
Data Index: 6655669 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3956. Min Act: -0.1700
Data Index: 5312314 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3868. Min Act: -0.1700
Data Index: 647211 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3780. Min Act: -0.1700
Data Index: 11411 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3780. Min Act: -0.1700
Data Index: 5465540 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3780. Min Act: -0.1700
Data Index: 6858386 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3780. Min Act: -0.1700
Data Index: 6713884 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3515. Min Act: -0.1700
Data Index: 925831 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3691. Min Act: -0.1700
Data Index: 3688577 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3691. Min Act: -0.1700
Data Index: 3300908 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3427. Min Act: -0.1700
Data Index: 5319369 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3603. Min Act: -0.1700
Data Index: 8243220 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3515. Min Act: -0.1700
Data Index: 1669194 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3515. Min Act: -0.1700
Data Index: 8663249 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3427. Min Act: -0.1628
Data Index: 7273167 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4396. Min Range: -1.4396
Max Act: 1.3427. Min Act: -0.1699
Data Index: 5797735 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #19