Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3781 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.9869. Min Act: -0.1700
Data Index: 408862 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.9394. Min Act: -0.1700
Data Index: 4780075 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.9236. Min Act: -0.1700
Data Index: 7048900 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.8601. Min Act: -0.1700
Data Index: 3926419 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.8442. Min Act: -0.1700
Data Index: 2784511 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.8601. Min Act: -0.1700
Data Index: 8220029 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.8442. Min Act: -0.1700
Data Index: 6079097 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.8283. Min Act: -0.1700
Data Index: 2539731 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7965. Min Act: -0.1700
Data Index: 5625624 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7965. Min Act: -0.1700
Data Index: 71549 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7965. Min Act: -0.1700
Data Index: 4790824 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7965. Min Act: -0.1700
Data Index: 8385051 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7965. Min Act: -0.1700
Data Index: 7862731 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7806. Min Act: -0.1700
Data Index: 7351017 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7806. Min Act: -0.1700
Data Index: 2719838 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7806. Min Act: -0.1700
Data Index: 6316841 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7646. Min Act: -0.1700
Data Index: 6403917 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7646. Min Act: -0.1700
Data Index: 4979880 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7487. Min Act: -0.1700
Data Index: 5096115 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9869. Min Range: -2.9869
Max Act: 2.7487. Min Act: -0.1700
Data Index: 257200 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19