Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2138 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.4157. Min Act: -0.1700
Data Index: 2175423 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.4157. Min Act: -0.1700
Data Index: 2542281 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3994. Min Act: -0.1700
Data Index: 262739 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3994. Min Act: -0.1700
Data Index: 592466 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3994. Min Act: -0.1700
Data Index: 4473420 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3667. Min Act: -0.1700
Data Index: 8494611 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3503. Min Act: -0.1700
Data Index: 6238825 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3503. Min Act: -0.1700
Data Index: 7564843 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3503. Min Act: -0.1700
Data Index: 7666723 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3339. Min Act: -0.1700
Data Index: 179889 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3175. Min Act: -0.1700
Data Index: 5856246 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3175. Min Act: -0.1700
Data Index: 4684838 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3175. Min Act: -0.1700
Data Index: 5457341 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3175. Min Act: -0.1700
Data Index: 121856 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3011. Min Act: -0.1700
Data Index: 2285827 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3011. Min Act: -0.1700
Data Index: 7909125 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.3011. Min Act: -0.1696
Data Index: 8435176 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.2846. Min Act: -0.1700
Data Index: 4308433 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.2846. Min Act: -0.1700
Data Index: 5821136 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4157. Min Range: -2.4157
Max Act: 2.2846. Min Act: -0.1700
Data Index: 4682054 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #19