Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5350 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1356. Min Range: -4.1356
Max Act: 4.1356. Min Act: -0.1700
Data Index: 8009008 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1356. Min Range: -4.1356
Max Act: 4.0105. Min Act: -0.1700
Data Index: 4551117 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1356. Min Range: -4.1356
Max Act: 4.0418. Min Act: -0.1700
Data Index: 6889199 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1356. Min Range: -4.1356
Max Act: 4.0418. Min Act: -0.1700
Data Index: 6668103 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9793. Min Act: -0.1700
Data Index: 4466163 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9793. Min Act: -0.1700
Data Index: 5465213 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 6845827 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9480. Min Act: -0.1700
Data Index: 2695145 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9480. Min Act: -0.1700
Data Index: 7615247 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 3161707 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 3057168 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 2908975 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 3568416 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 1294411 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 680757 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.9168. Min Act: -0.1700
Data Index: 1082681 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.8855. Min Act: -0.1700
Data Index: 680755 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.8855. Min Act: -0.1700
Data Index: 6472509 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.8855. Min Act: -0.1700
Data Index: 5341852 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1356. Min Range: -4.1356
Max Act: 3.8855. Min Act: -0.1700
Data Index: 6762993 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #19