Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2982 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.4543. Min Act: -0.1700
Data Index: 1655233 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3918. Min Act: -0.1700
Data Index: 5042615 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.4230. Min Act: -0.1700
Data Index: 7470995 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.4230. Min Act: -0.1700
Data Index: 70886 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.4230. Min Act: -0.1700
Data Index: 2355999 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3918. Min Act: -0.1700
Data Index: 1152426 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3918. Min Act: -0.1700
Data Index: 404305 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3918. Min Act: -0.1700
Data Index: 7544131 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 1461621 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 8757217 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 8042094 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 7868324 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 3806300 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.2980. Min Act: -0.1700
Data Index: 7062729 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3293. Min Act: -0.1700
Data Index: 4386421 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3605. Min Act: -0.1700
Data Index: 5656393 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3293. Min Act: -0.1700
Data Index: 7363934 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3293. Min Act: -0.1700
Data Index: 5083959 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.2980. Min Act: -0.1700
Data Index: 1390189 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4543. Min Range: -5.4543
Max Act: 5.3293. Min Act: -0.1700
Data Index: 5139702 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19