Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4418 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.5711. Min Act: -0.1700
Data Index: 8276884 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.5711. Min Act: -0.1700
Data Index: 198594 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.2898. Min Act: -0.1700
Data Index: 1187278 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.2273. Min Act: -0.1700
Data Index: 6053096 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.2273. Min Act: -0.1700
Data Index: 3777447 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1961. Min Act: -0.1700
Data Index: 6009638 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1961. Min Act: -0.1700
Data Index: 2498308 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1336. Min Act: -0.1700
Data Index: 1170118 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1648. Min Act: -0.1700
Data Index: 4628996 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1336. Min Act: -0.1700
Data Index: 4121001 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1336. Min Act: -0.1700
Data Index: 3341647 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1336. Min Act: -0.1700
Data Index: 2733345 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1023. Min Act: -0.1700
Data Index: 4611037 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1023. Min Act: -0.1700
Data Index: 639906 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.1023. Min Act: -0.1700
Data Index: 3726528 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.0711. Min Act: -0.1700
Data Index: 7645868 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.0711. Min Act: -0.1700
Data Index: 3526600 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.0711. Min Act: -0.1700
Data Index: 2543736 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.0711. Min Act: -0.1700
Data Index: 4262942 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5711. Min Range: -5.5711
Max Act: 5.0398. Min Act: -0.1700
Data Index: 3813281 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #19