Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1017 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.6112. Min Act: -0.1700
Data Index: 8764022 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.4862. Min Act: -0.1700
Data Index: 6845710 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.4550. Min Act: -0.1700
Data Index: 5840912 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.4237. Min Act: -0.1700
Data Index: 6465589 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.3612. Min Act: -0.1700
Data Index: 3750035 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2987. Min Act: -0.1700
Data Index: 3007365 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.3300. Min Act: -0.1700
Data Index: 634506 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2987. Min Act: -0.1700
Data Index: 401802 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2675. Min Act: -0.1700
Data Index: 1302521 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2675. Min Act: -0.1700
Data Index: 4087312 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2362. Min Act: -0.1700
Data Index: 6459564 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2050. Min Act: -0.1700
Data Index: 8318238 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.2050. Min Act: -0.1700
Data Index: 4530350 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1737. Min Act: -0.1700
Data Index: 5652184 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.0800. Min Act: -0.1700
Data Index: 277228 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1112. Min Act: -0.1700
Data Index: 2806243 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1112. Min Act: -0.1700
Data Index: 8208209 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.1112. Min Act: -0.1700
Data Index: 8045055 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.0800. Min Act: -0.1700
Data Index: 4958594 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6112. Min Range: -6.6112
Max Act: 6.0800. Min Act: -0.1700
Data Index: 8241739 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19