Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4054 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.6233. Min Act: -0.1700
Data Index: 3199169 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.5295. Min Act: -0.1700
Data Index: 1939516 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.4045. Min Act: -0.1700
Data Index: 1448144 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.3420. Min Act: -0.1700
Data Index: 3646096 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.3108. Min Act: -0.1700
Data Index: 1905675 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.3108. Min Act: -0.1700
Data Index: 1199455 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.2483. Min Act: -0.1700
Data Index: 2788412 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.2483. Min Act: -0.1700
Data Index: 2001205 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1858. Min Act: -0.1700
Data Index: 8831177 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1858. Min Act: -0.1700
Data Index: 6701114 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1858. Min Act: -0.1700
Data Index: 3949391 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1858. Min Act: -0.1700
Data Index: 7340720 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1545. Min Act: -0.1700
Data Index: 6867238 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 6163169 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1545. Min Act: -0.1700
Data Index: 2253690 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 137672 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 4044142 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 1629840 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1233. Min Act: -0.1700
Data Index: 504571 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6233. Min Range: -6.6233
Max Act: 6.1545. Min Act: -0.1700
Data Index: 7637903 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #19