Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5420 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.5461. Min Act: -0.1700
Data Index: 6725170 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.3586. Min Act: -0.1700
Data Index: 5039702 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.4836. Min Act: -0.1700
Data Index: 5213344 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.2961. Min Act: -0.1700
Data Index: 8491711 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.3586. Min Act: -0.1700
Data Index: 2230237 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.2961. Min Act: -0.1700
Data Index: 8249798 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.2961. Min Act: -0.1700
Data Index: 6614181 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5461. Min Range: -9.5461
Max Act: 9.1086. Min Act: -0.1700
Data Index: 7998220 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.9836. Min Act: -0.1700
Data Index: 2559770 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.9836. Min Act: -0.1700
Data Index: 1144835 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.9836. Min Act: -0.1700
Data Index: 7735175 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.9211. Min Act: -0.1700
Data Index: 5232131 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.8586. Min Act: -0.1700
Data Index: 2440923 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.9211. Min Act: -0.1700
Data Index: 5039703 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.8586. Min Act: -0.1700
Data Index: 7129709 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.7961. Min Act: -0.1700
Data Index: 6963282 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.7961. Min Act: -0.1700
Data Index: 1497306 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.7961. Min Act: -0.1700
Data Index: 7230587 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.7961. Min Act: -0.1700
Data Index: 294127 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5461. Min Range: -9.5461
Max Act: 8.7336. Min Act: -0.1700
Data Index: 5183283 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19