Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 797 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.9613. Min Act: -0.1700
Data Index: 185221 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.9457. Min Act: -0.1700
Data Index: 2844614 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.9144. Min Act: -0.1700
Data Index: 8015748 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8988. Min Act: -0.1700
Data Index: 7176715 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8988. Min Act: -0.1700
Data Index: 2335927 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8675. Min Act: -0.1700
Data Index: 8017163 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8675. Min Act: -0.1700
Data Index: 2844626 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8832. Min Act: -0.1700
Data Index: 4848471 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8832. Min Act: -0.1700
Data Index: 3733681 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8519. Min Act: -0.1700
Data Index: 4618191 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8363. Min Act: -0.1700
Data Index: 4835942 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8519. Min Act: -0.1700
Data Index: 6185324 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8050. Min Act: -0.1700
Data Index: 6861929 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8206. Min Act: -0.1700
Data Index: 1018229 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8206. Min Act: -0.1700
Data Index: 7460519 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8050. Min Act: -0.1700
Data Index: 7352816 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8206. Min Act: -0.1700
Data Index: 7002912 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8206. Min Act: -0.1700
Data Index: 4611852 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.8206. Min Act: -0.1700
Data Index: 1638603 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9613. Min Range: -3.9613
Max Act: 3.7894. Min Act: -0.1700
Data Index: 4338748 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19