Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 484 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.3292. Min Act: -0.1700
Data Index: 3397132 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1730. Min Act: -0.1700
Data Index: 3672274 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 7593362 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 1870646 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 6579920 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1417. Min Act: -0.1700
Data Index: 6704376 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 5126204 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0792. Min Act: -0.1700
Data Index: 6113248 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 5343738 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 1312889 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0792. Min Act: -0.1700
Data Index: 8415427 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 5111709 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 7216615 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 7428512 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.1105. Min Act: -0.1700
Data Index: 8066297 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0480. Min Act: -0.1700
Data Index: 3623864 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3292. Min Range: -5.3292
Max Act: 4.9855. Min Act: -0.1700
Data Index: 5237978 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0480. Min Act: -0.1700
Data Index: 1926349 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0167. Min Act: -0.1700
Data Index: 1988222 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3292. Min Range: -5.3292
Max Act: 5.0167. Min Act: -0.1700
Data Index: 5724242 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19