Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2898 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.7646. Min Act: -0.1700
Data Index: 6019101 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.6396. Min Act: -0.1700
Data Index: 3023934 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.4833. Min Act: -0.1700
Data Index: 3552034 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.4208. Min Act: -0.1700
Data Index: 8625279 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4093026 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2958. Min Act: -0.1700
Data Index: 6202485 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2958. Min Act: -0.1700
Data Index: 4542444 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2646. Min Act: -0.1700
Data Index: 1307158 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2958. Min Act: -0.1700
Data Index: 6245044 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2646. Min Act: -0.1700
Data Index: 7778482 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2333. Min Act: -0.1700
Data Index: 182951 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2333. Min Act: -0.1700
Data Index: 3200282 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2021. Min Act: -0.1700
Data Index: 845803 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1001352 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.2021. Min Act: -0.1700
Data Index: 1001351 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.1396. Min Act: -0.1700
Data Index: 3185689 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.1708. Min Act: -0.1700
Data Index: 7106859 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.1396. Min Act: -0.1700
Data Index: 5036419 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.1396. Min Act: -0.1700
Data Index: 2889880 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7646. Min Range: -5.7646
Max Act: 5.1396. Min Act: -0.1700
Data Index: 1416037 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19