Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2186 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.7244. Min Act: -0.1700
Data Index: 8628628 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.6932. Min Act: -0.1700
Data Index: 8671357 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.6932. Min Act: -0.1700
Data Index: 1282995 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.6619. Min Act: -0.1700
Data Index: 7830471 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.6307. Min Act: -0.1700
Data Index: 1146974 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.5682. Min Act: -0.1700
Data Index: 5789594 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.5057. Min Act: -0.1700
Data Index: 3356650 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.5369. Min Act: -0.1700
Data Index: 3965964 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.5057. Min Act: -0.1700
Data Index: 7685102 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.5369. Min Act: -0.1700
Data Index: 7363311 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4744. Min Act: -0.1700
Data Index: 3607582 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 5471987 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 7151909 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 8733757 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 3634053 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4432. Min Act: -0.1700
Data Index: 8338555 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.3807. Min Act: -0.1700
Data Index: 286777 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.4119. Min Act: -0.1700
Data Index: 8701369 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.3494. Min Act: -0.1700
Data Index: 8788147 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7244. Min Range: -7.7244
Max Act: 7.3807. Min Act: -0.1700
Data Index: 8014635 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19