Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2048 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.5808. Min Act: -0.1700
Data Index: 393875 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.4558. Min Act: -0.1700
Data Index: 6785157 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.4558. Min Act: -0.1700
Data Index: 4282567 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.3933. Min Act: -0.1700
Data Index: 1648344 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.3933. Min Act: -0.1700
Data Index: 7651822 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.3308. Min Act: -0.1700
Data Index: 691262 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.2683. Min Act: -0.1700
Data Index: 3404159 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.2683. Min Act: -0.1700
Data Index: 1943920 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.2058. Min Act: -0.1700
Data Index: 444258 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.1433. Min Act: -0.1700
Data Index: 6102264 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.1433. Min Act: -0.1700
Data Index: 8663836 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.1433. Min Act: -0.1700
Data Index: 5100069 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 8602942 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 8565845 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0183. Min Act: -0.1700
Data Index: 7879430 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 7797487 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0808. Min Act: -0.1700
Data Index: 5212458 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0183. Min Act: -0.1700
Data Index: 1340680 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5808. Min Range: -9.5808
Max Act: 8.9558. Min Act: -0.1700
Data Index: 1998083 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5808. Min Range: -9.5808
Max Act: 9.0183. Min Act: -0.1700
Data Index: 3350651 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #19