Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4403 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.7026. Min Act: -0.1700
Data Index: 7940765 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.7026. Min Act: -0.1700
Data Index: 7343117 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.5464. Min Act: -0.1700
Data Index: 1254965 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.5151. Min Act: -0.1700
Data Index: 4163115 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.4526. Min Act: -0.1700
Data Index: 1332092 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.4214. Min Act: -0.1700
Data Index: 4702081 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.4214. Min Act: -0.1700
Data Index: 4702078 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.3901. Min Act: -0.1700
Data Index: 1878526 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.4214. Min Act: -0.1700
Data Index: 3744759 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.3901. Min Act: -0.1700
Data Index: 1229585 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.3901. Min Act: -0.1700
Data Index: 741981 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.3589. Min Act: -0.1700
Data Index: 7087592 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.3276. Min Act: -0.1700
Data Index: 3616981 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.2964. Min Act: -0.1700
Data Index: 7101459 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.2964. Min Act: -0.1700
Data Index: 8672795 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.2651. Min Act: -0.1700
Data Index: 7337909 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.2339. Min Act: -0.1700
Data Index: 7791261 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.2339. Min Act: -0.1700
Data Index: 2449850 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.1401. Min Act: -0.1700
Data Index: 2744114 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7026. Min Range: -6.7026
Max Act: 6.1714. Min Act: -0.1700
Data Index: 3652980 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #19