Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2602 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.5906. Min Act: -0.1700
Data Index: 3292567 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.2468. Min Act: -0.1700
Data Index: 7296809 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.2156. Min Act: -0.1700
Data Index: 7688290 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.1531. Min Act: -0.1700
Data Index: 3801591 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.1218. Min Act: -0.1700
Data Index: 6699857 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.0593. Min Act: -0.1700
Data Index: 2272992 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.1218. Min Act: -0.1700
Data Index: 1552455 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5906. Min Range: -5.5906
Max Act: 5.0281. Min Act: -0.1700
Data Index: 726067 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.9968. Min Act: -0.1700
Data Index: 2941971 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4939812 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 7989072 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 8231389 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 3543651 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8093. Min Act: -0.1700
Data Index: 557997 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 119739 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 4560911 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8406. Min Act: -0.1700
Data Index: 8381186 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.7781. Min Act: -0.1700
Data Index: 2954689 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.8093. Min Act: -0.1700
Data Index: 3346770 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5906. Min Range: -5.5906
Max Act: 4.7781. Min Act: -0.1700
Data Index: 497430 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19