Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4338 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.8286. Min Act: -0.1700
Data Index: 6772299 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.7661. Min Act: -0.1700
Data Index: 8278505 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.7036. Min Act: -0.1700
Data Index: 6772305 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5786. Min Act: -0.1700
Data Index: 7801361 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5786. Min Act: -0.1700
Data Index: 6772297 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6772303 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5473. Min Act: -0.1700
Data Index: 2467857 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5473. Min Act: -0.1700
Data Index: 6772302 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5161. Min Act: -0.1700
Data Index: 6772298 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.5161. Min Act: -0.1700
Data Index: 1553857 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.4848. Min Act: -0.1700
Data Index: 1687956 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.4848. Min Act: -0.1700
Data Index: 4503394 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.4223. Min Act: -0.1700
Data Index: 4503401 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.3911. Min Act: -0.1700
Data Index: 3151456 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.3911. Min Act: -0.1700
Data Index: 6786674 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.3598. Min Act: -0.1700
Data Index: 7172380 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.3286. Min Act: -0.1700
Data Index: 4750198 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.2973. Min Act: -0.1700
Data Index: 5906333 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.2348. Min Act: -0.1700
Data Index: 8066554 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8286. Min Range: -5.8286
Max Act: 5.2348. Min Act: -0.1700
Data Index: 7643016 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #19