Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 465 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.5213. Min Act: -0.1700
Data Index: 3549453 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.4588. Min Act: -0.1700
Data Index: 777089 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3338. Min Act: -0.1700
Data Index: 6666317 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3338. Min Act: -0.1700
Data Index: 7911969 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3026. Min Act: -0.1700
Data Index: 4626715 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3651. Min Act: -0.1700
Data Index: 2173851 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3338. Min Act: -0.1700
Data Index: 6591950 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3026. Min Act: -0.1700
Data Index: 5412564 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2713. Min Act: -0.1700
Data Index: 7900722 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3338. Min Act: -0.1700
Data Index: 1922891 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2713. Min Act: -0.1700
Data Index: 3797529 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.3026. Min Act: -0.1700
Data Index: 2122350 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2401. Min Act: -0.1700
Data Index: 821938 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2713. Min Act: -0.1700
Data Index: 8699990 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2713. Min Act: -0.1700
Data Index: 8575878 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2713. Min Act: -0.1700
Data Index: 4626841 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2401. Min Act: -0.1700
Data Index: 2487308 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2401. Min Act: -0.1700
Data Index: 6498940 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 5579293 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5213. Min Range: -5.5213
Max Act: 5.2088. Min Act: -0.1700
Data Index: 2169853 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19