Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0808. Min Range: -4.0808
Max Act: 4.0808. Min Act: -0.1700
Data Index: 3073733 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0808. Min Range: -4.0808
Max Act: 4.0183. Min Act: -0.1700
Data Index: 4016043 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.9870. Min Act: -0.1700
Data Index: 132893 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.9870. Min Act: -0.1700
Data Index: 8350539 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.9558. Min Act: -0.1700
Data Index: 7007244 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.9558. Min Act: -0.1700
Data Index: 7058701 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8620. Min Act: -0.1700
Data Index: 8137753 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8933. Min Act: -0.1700
Data Index: 728032 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8933. Min Act: -0.1700
Data Index: 2956590 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8620. Min Act: -0.1700
Data Index: 7596184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8620. Min Act: -0.1700
Data Index: 1187689 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8620. Min Act: -0.1700
Data Index: 5897378 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8307. Min Act: -0.1700
Data Index: 5398299 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8151. Min Act: -0.1700
Data Index: 7423715 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.8151. Min Act: -0.1700
Data Index: 2423710 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.7994. Min Act: -0.1700
Data Index: 3406697 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.7994. Min Act: -0.1700
Data Index: 5031429 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.7994. Min Act: -0.1700
Data Index: 6625977 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.7994. Min Act: -0.1700
Data Index: 1248509 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0808. Min Range: -4.0808
Max Act: 3.7682. Min Act: -0.1700
Data Index: 775576 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19