Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1820 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.3373. Min Act: -0.1700
Data Index: 5577270 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.2748. Min Act: -0.1700
Data Index: 4896821 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.1811. Min Act: -0.1700
Data Index: 2583251 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.2123. Min Act: -0.1700
Data Index: 2237725 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 3232343 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.1811. Min Act: -0.1700
Data Index: 3232345 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.1498. Min Act: -0.1700
Data Index: 1236043 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.1186. Min Act: -0.1700
Data Index: 6058887 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.0561. Min Act: -0.1700
Data Index: 6975854 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.0248. Min Act: -0.1700
Data Index: 4880705 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.0248. Min Act: -0.1700
Data Index: 2866205 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.0561. Min Act: -0.1700
Data Index: 5251224 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3373. Min Range: -5.3373
Max Act: 5.0561. Min Act: -0.1700
Data Index: 194497 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9936. Min Act: -0.1700
Data Index: 4664 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9936. Min Act: -0.1700
Data Index: 2673567 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9311. Min Act: -0.1700
Data Index: 1677496 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9623. Min Act: -0.1700
Data Index: 8514205 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9623. Min Act: -0.1700
Data Index: 6131543 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9311. Min Act: -0.1700
Data Index: 5577273 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3373. Min Range: -5.3373
Max Act: 4.9311. Min Act: -0.1700
Data Index: 5312245 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19