Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2002 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.4146. Min Act: -0.1700
Data Index: 3373906 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.2583. Min Act: -0.1700
Data Index: 8268611 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.2271. Min Act: -0.1700
Data Index: 2708934 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.1958. Min Act: -0.1700
Data Index: 2849173 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.1646. Min Act: -0.1700
Data Index: 611556 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.1958. Min Act: -0.1700
Data Index: 8340585 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.1333. Min Act: -0.1700
Data Index: 8233711 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.0396. Min Act: -0.1700
Data Index: 3405612 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.0708. Min Act: -0.1700
Data Index: 6770445 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4146. Min Range: -7.4146
Max Act: 7.0083. Min Act: -0.1700
Data Index: 8244791 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 3152033 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 7769838 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 991698 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 1823056 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 4901977 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9146. Min Act: -0.1700
Data Index: 1353760 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.9458. Min Act: -0.1700
Data Index: 6537621 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.8521. Min Act: -0.1700
Data Index: 7967283 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.8833. Min Act: -0.1700
Data Index: 7426654 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4146. Min Range: -7.4146
Max Act: 6.8833. Min Act: -0.1700
Data Index: 2746644 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #19