Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4535 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.4940. Min Act: -0.1700
Data Index: 6076528 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.4315. Min Act: -0.1700
Data Index: 5744122 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.4315. Min Act: -0.1700
Data Index: 466090 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.3690. Min Act: -0.1700
Data Index: 362499 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.3377. Min Act: -0.1700
Data Index: 1285325 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.3065. Min Act: -0.1700
Data Index: 6765440 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.2752. Min Act: -0.1700
Data Index: 8329515 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.2440. Min Act: -0.1700
Data Index: 1271995 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.2127. Min Act: -0.1700
Data Index: 5088676 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.2127. Min Act: -0.1700
Data Index: 3914320 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1502. Min Act: -0.1700
Data Index: 4430115 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 6119367 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 45289 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 4091532 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 854608 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1502. Min Act: -0.1700
Data Index: 8108838 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 1521449 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1815. Min Act: -0.1700
Data Index: 3177548 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1502. Min Act: -0.1700
Data Index: 4215269 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4940. Min Range: -4.4940
Max Act: 4.1190. Min Act: -0.1700
Data Index: 664969 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #19