Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4084 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.3292. Min Act: -0.1700
Data Index: 8728013 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.3292. Min Act: -0.1700
Data Index: 1584728 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.2980. Min Act: -0.1700
Data Index: 8089556 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.2980. Min Act: -0.1700
Data Index: 5140938 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.2667. Min Act: -0.1700
Data Index: 1553963 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.2355. Min Act: -0.1700
Data Index: 2673299 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.1417. Min Act: -0.1700
Data Index: 1638977 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.1105. Min Act: -0.1700
Data Index: 2183017 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.1105. Min Act: -0.1700
Data Index: 6017751 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.0480. Min Act: -0.1700
Data Index: 7401574 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.0480. Min Act: -0.1700
Data Index: 611013 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3292. Min Range: -7.3292
Max Act: 7.0167. Min Act: -0.1700
Data Index: 615536 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9855. Min Act: -0.1700
Data Index: 6862028 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9855. Min Act: -0.1700
Data Index: 5641830 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9855. Min Act: -0.1700
Data Index: 1045766 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9855. Min Act: -0.1700
Data Index: 5112525 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9855. Min Act: -0.1700
Data Index: 1982225 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9542. Min Act: -0.1700
Data Index: 3738142 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9230. Min Act: -0.1700
Data Index: 2807253 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3292. Min Range: -7.3292
Max Act: 6.9230. Min Act: -0.1700
Data Index: 5330855 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19